diagnose_retrieval
Explain why a specific note was or was not returned for a query. Re-runs the retrieval pipeline with per-stage tracing and reports, for that one note, where it was present, its score and rank where a stage produces them, and the first stage that dropped it. Read-only and non-mutating; reports nothing about paths the caller cannot read. response_format=concise returns returned, dropped_at and summary without the per-stage trace.
| Domain | knowledge |
| Scopes | read:notes |
| Access | read |
| Tags | read-only, domain:knowledge, knowledge, search, diagnostics, external-network |
| Profile | core, full |
Annotations
Section titled “Annotations”| 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.
Confirmation (human in the loop)
Section titled “Confirmation (human in the loop)”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_-]+$ |
|
query |
string |
yes | — | length ≥ 1 |
path |
string |
yes | — | length 1–1024 |
final_top_k |
integer |
10 |
range 1–100 | |
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" |
Output
Section titled “Output”| Field | Type | Always present | Description |
|---|---|---|---|
vault |
string |
yes | — |
query |
string |
— | |
path |
string |
— | |
returned |
boolean |
yes | — |
dropped_at |
string | null |
yes | — |
summary |
string |
yes | — |
stages |
object[] |
— | |
stages[].stage |
string |
with parent | — |
stages[].present |
boolean |
with parent | — |
stages[].chunks_present |
number |
with parent | — |
stages[].candidates_in |
number |
with parent | — |
stages[].candidates_out |
number |
with parent | — |
stages[].score |
number |
— | |
stages[].rank |
number |
— | |
stages[].note |
string |
— |
Related tools
Section titled “Related tools”Other tools in the knowledge domain: add_observation, audit_provenance, close_goal, commit_capture, commit_wiki_page, create_entity, delete_entity, draft_wiki_page, end_session, enqueue_capture, episode_stats, explain_answer, 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.