Skip to content

explain_answer

Explain what an answer actually used: walks retrieval -> chunk -> citation -> episode for one session or time window and reports each link with how well it is known. Distinguishes a retrieval the citation pass never judged from one it judged and rejected, and a chunk whose note no longer exists from one that was never used. Read-only; reports nothing about paths the caller cannot read. response_format=concise drops the summary counts and each link’s retrieval echo (time, surface, query text, rank); the caveat and the citation-pass record stay.

Domain knowledge
Scopes read:notes
Access read
Tags read-only, domain:knowledge, knowledge, provenance, diagnostics
Profile core, full
Annotation Value
Read-only yes
Destructive no
Idempotent no
Accepts an idempotency key no

Idempotent is the advisory MCP idempotentHint. Destructive is also yes for a tool that asks for confirmation only on some calls.

No human confirmation is required to call this tool.

Parameter Type Required Default Description
vault string — Vault id. May be omitted when only one vault is available. length 1–64; pattern ^[a-z0-9_-]+$
session_id string — length ≥ 1
since integer — range ≥ 0
until integer — range ≥ 0
limit integer 50 range 1–200
response_format enum — concise returns only the high-signal fields; detailed (the shipped default) returns the full payload. Errors and safety warnings are never trimmed. When omitted, the server’s tools.defaults.responseFormat applies. One of: "concise", "detailed"
verbosity enum — Legacy alias for response_format: terse = concise, full = detailed. One of: "full", "terse"
Field Type Always present Description
available boolean yes —
message string —
vault string —
scope enum One of: "session", "time_window"
links object[] —
links[].chunk_id string with parent —
links[].path string | null with parent —
links[].chunk enum with parent One of: "resolved", "deleted"
links[].retrieved_at number —
links[].surface_type string —
links[].query_text string | null —
links[].rank_in_results number | null —
links[].citation enum with parent One of: "confirmed", "rejected", "candidate", "uncertain", "not_stamped"
links[].citation_score number | null with parent —
links[].correlation enum with parent One of: "session", "time_window", "none"
links[].episode_id string | null —
summary object —
summary.retrievals number with parent —
summary.deleted_chunks number with parent —
summary.not_stamped number with parent —
summary.not_cited number with parent —
summary.cited number with parent —
summary.exact_correlations number with parent —
caveat string | null —
citation_pass object —
citation_pass.recorded_runs number with parent —
citation_pass.last_ran_at number | null with parent —
citation_pass.last_aborted boolean with parent —
citation_pass.last_unfinished boolean with parent —

Other tools in the knowledge domain: add_observation, audit_provenance, close_goal, commit_capture, commit_wiki_page, create_entity, delete_entity, diagnose_retrieval, draft_wiki_page, end_session, enqueue_capture, episode_stats, find_existing_page, gap_report, get_entity, get_session_traces, knowledge_challenge, link_entities, lint_wiki, list_capture_queue, list_contradictions, list_goals, note_quality_report, plur_get, plur_recall, plur_recall_hybrid, plur_similarity_search, query_entity_graph, record_retrieval_feedback, reflect, rename_entity, session_bootstrap, set_goal, start_session, unlink_entities, update_observation, vault_context, vault_graph_search, work_episode_chain, work_episodes, work_forget, work_result, work_search.

Back to the tool catalog.