Skip to main content
Glama

Recall

crbro_recall
Read-onlyIdempotent

Search everything saved in earlier sessions before answering questions about the user, projects, preferences, or past decisions. Returns ranked matches with confidence and origin, so you confirm stored facts instead of guessing.

Instructions

Read-only search of everything saved in earlier sessions. Call it BEFORE answering anything about the user, their projects, preferences, decisions or past work: the answer is usually stored. One row per neuron: the best entry (matching_content; entry_id → crbro_inspect view=neuron entries=[id] reads it whole), confidence (weak: verify; a search match, not truth) and also_matched previews. Absent fields hold their default: temporal current_claim, verification none (present = a check the caller reported), freshness unverified, provenance local. Lines not the user's own carry origin, also_matched too: team: with self-declared by, or miner. Rows past their shelf life move to possibly_stale as last_known with a next_step: check before answering with one. has_map: read crbro_map before touching that system.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "crbro_recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoOnly these entry kinds, e.g. ["error"] before repeating a mistake. Leaves out day logs.
limitNoRows, default 5.
queryYesWhat to look for; a few distinctive terms beat a sentence.
scopeNoauto (default) ranks the bound project first; project restricts to it; all ignores it.
sinceNoA day ("2026-09-01") or span ("7d", "2w", "3m"); undated entries are skipped and counted.
domainNoOnly neurons of this exact domain.
intentNocurrent splits historical records into historical_matches; history keeps only them; any (default).
neuronsNoOnly these neuron ids; no day logs.
projectNoProject id or alias; default the boot project of this connection.
queriesNoOther phrasings searched with query and fused: synonyms, the other language, product names. 2-4.

Output Schema

NameRequiredDescriptionDefault
hintYes
queryYes
resultsYes
has_moreNo
returnedNo
semanticNowarming: model still loading, keyword-only answer
no_answerNoNothing cleared the evidence bar: at most 3 weak rows, the nearest
stale_warningNo
total_resultsYes
possibly_staleNo
sessions_matchedNo
historical_matchesNo
possibly_stale_countNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed54 schema fields changedv2.12.0
    • changedInput schema / properties / domain / description
      Previous value: -"Only neurons in this domain (exact match, e.g. \"proyectos-web\"). Day logs have no domain: sessions_matched is listed regardless."New value: +"Only neurons of this exact domain."
    • changedInput schema / properties / intent / description
      Previous value: -"current separates historical/imported records into historical_matches; history returns historical records among the ranked candidates, not retired entries; any preserves both. No source is checked automatically."New value: +"current splits historical records into historical_matches; history keeps only them; any (default)."
    • changedInput schema / properties / kind / description
      Previous value: -"Only these entry kinds, e.g. [\"error\"] for past mistakes before repeating one, [\"decision\"] for what was agreed and why, [\"debt\"] for what was deferred. Day logs are left out when set."New value: +"Only these entry kinds, e.g. [\"error\"] before repeating a mistake. Leaves out day logs."
    • changedInput schema / properties / limit / description
      Previous value: -"Max neurons returned (default 5, ranked; ask for more only when the top five did not answer)."New value: +"Rows, default 5."
    • changedInput schema / properties / neurons / description
      Previous value: -"Explicit neuron-id allowlist, applied before ranking and limit; excludes day logs."New value: +"Only these neuron ids; no day logs."
    • changedInput schema / properties / project / description
      Previous value: -"Registered project id or alias; omitted uses this connection's boot project."New value: +"Project id or alias; default the boot project of this connection."
    • changedInput schema / properties / queries / description
      Previous value: -"Alternative phrasings of the same question, searched together with query and fused by rank. Use synonyms, the other language and the concrete product name; 2-4 is plenty."New value: +"Other phrasings searched with query and fused: synonyms, the other language, product names. 2-4."
    • changedInput schema / properties / query / description
      Previous value: -"What to look for, e.g. \"Firebase authentication setup\". Fewer, distinctive terms beat full sentences."New value: +"What to look for; a few distinctive terms beat a sentence."
    • changedInput schema / properties / scope / description
      Previous value: -"auto prioritizes the current bound project without hiding other matches; project restricts it plus global preferences/lessons; all ignores the connection project. Organization, not access control."New value: +"auto (default) ranks the bound project first; project restricts to it; all ignores it."
    • changedInput schema / properties / since / description
      Previous value: -"Only entries recorded on or after this: a day (\"2026-09-01\") or a span back from today (\"7d\", \"2w\", \"3m\"). For \"what changed lately\" and to keep an old telling out. A later verification does not make an old entry new. Undated entries cannot prove they are recent: they are left out and counted in undated_skipped."New value: +"A day (\"2026-09-01\") or span (\"7d\", \"2w\", \"3m\"); undated entries are skipped and counted."
    • changedOutput schema / additionalProperties
      Previous value: -falseNew value: +{}
    • removedOutput schema / properties / excluded_nonhistorical
      Removed value: -{
      -  "type": "number"
      -}
    • removedOutput schema / properties / filters
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "kind": {
      -      "items": {
      -        "type": "string"
      -      },
      -      "type": "array"
      -    },
      -    "since": {
      -      "type": "string"
      -    }
      -  },
      -  "type": "object"
      -}
    • removedOutput schema / properties / historical_matches / items / additionalProperties
      Removed value: -{}
    • removedOutput schema / properties / historical_matches / items / properties
      Removed value: -{}
    • removedOutput schema / properties / historical_matches / items / type
      Removed value: -"object"
    • removedOutput schema / properties / matched_neurons
      Removed value: -{
      -  "description": "Neurons with any hit before limit; total_results is what came back",
      -  "type": "number"
      -}
    • addedOutput schema / properties / no_answer
      Added value: +{
      +  "description": "Nothing cleared the evidence bar: at most 3 weak rows, the nearest",
      +  "type": "boolean"
      +}
    • removedOutput schema / properties / possibly_stale / description
      Removed value: -"Rows whose best entry is past its shelf life since last verified: warning, next_step (what to check before answering), the entry as last_known instead of matching_content, then the rest of a results row plus age_days, last_verified, shelf_life, shelf_inferred"
    • removedOutput schema / properties / possibly_stale / items / properties / age_days
      Removed value: -{
      -  "type": "number"
      -}
    • removedOutput schema / properties / possibly_stale / items / properties / last_verified
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / possibly_stale / items / properties / shelf_inferred
      Removed value: -{
      -  "type": "boolean"
      -}
    • removedOutput schema / properties / possibly_stale / items / properties / shelf_life
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / possibly_stale / items / properties / warning
      Removed value: -{
      -  "type": "string"
      -}
    • changedOutput schema / properties / possibly_stale / items / required
      Previous value: -[
      -  "warning",
      -  "next_step",
      -  "last_known",
      -  "neuron_id",
      -  "age_days",
      -  "last_verified",
      -  "shelf_life",
      -  "shelf_inferred"
      -]New value: +[
      +  "next_step",
      +  "last_known",
      +  "neuron_id"
      +]
    • removedOutput schema / properties / results / items / properties / also_matched / items / properties / added
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / results / items / properties / also_matched / items / properties / by
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / results / items / properties / also_matched / items / properties / chars
      Removed value: -{
      -  "type": "number"
      -}
    • removedOutput schema / properties / results / items / properties / also_matched / items / properties / entry_id
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / results / items / properties / also_matched / items / properties / kind
      Removed value: -{
      -  "type": "string"
      -}
    • changedOutput schema / properties / results / items / properties / also_matched / items / required
      Previous value: -[
      -  "kind",
      -  "added",
      -  "preview",
      -  "chars"
      -]New value: +[
      +  "preview"
      +]
    • removedOutput schema / properties / results / items / properties / by
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / results / items / properties / content_chars
      Removed value: -{
      -  "type": "number"
      -}
    • removedOutput schema / properties / results / items / properties / content_truncated
      Removed value: -{
      -  "type": "boolean"
      -}
    • removedOutput schema / properties / results / items / properties / domain
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / results / items / properties / has_map
      Removed value: -{
      -  "type": "boolean"
      -}
    • removedOutput schema / properties / results / items / properties / heat
      Removed value: -{
      -  "type": "number"
      -}
    • removedOutput schema / properties / results / items / properties / matched_added
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / results / items / properties / matched_kind
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / results / items / properties / matched_terms
      Removed value: -{
      -  "type": "number"
      -}
    • removedOutput schema / properties / results / items / properties / query_terms
      Removed value: -{
      -  "type": "number"
      -}
    • removedOutput schema / properties / results / items / properties / rank
      Removed value: -{
      -  "description": "Position in the ranking, set when some row moved to possibly_stale",
      -  "type": "number"
      -}
    • removedOutput schema / properties / results / items / properties / relevance_score
      Removed value: -{
      -  "type": "number"
      -}
    • changedOutput schema / properties / results / items / required
      Previous value: -[
      -  "neuron_id",
      -  "name",
      -  "domain",
      -  "relevance_score",
      -  "matching_content",
      -  "heat"
      -]New value: +[
      +  "neuron_id",
      +  "name",
      +  "matching_content"
      +]
    • removedOutput schema / properties / returned / description
      Removed value: -"Rows that came back: results plus possibly_stale"
    • removedOutput schema / properties / search_scope
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "mode": {
      -      "type": "string"
      -    },
      -    "neurons": {
      -      "items": {
      -        "type": "string"
      -      },
      -      "type": "array"
      -    },
      -    "project_id": {
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "mode"
      -  ],
      -  "type": "object"
      -}
    • addedOutput schema / properties / semantic
      Added value: +{
      +  "description": "warming: model still loading, keyword-only answer",
      +  "type": "string"
      +}
    • removedOutput schema / properties / sessions_matched / items / additionalProperties
      Removed value: -{}
    • removedOutput schema / properties / sessions_matched / items / properties
      Removed value: -{}
    • removedOutput schema / properties / sessions_matched / items / type
      Removed value: -"object"
    • removedOutput schema / properties / sessions_total
      Removed value: -{
      -  "type": "number"
      -}
    • removedOutput schema / properties / stale_warning / description
      Removed value: -"Set, first, when some row moved to possibly_stale: do not answer with those as current"
    • removedOutput schema / properties / truncated
      Removed value: -{
      -  "additionalProperties": {},
      -  "properties": {},
      -  "type": "object"
      -}
    • removedOutput schema / properties / undated_skipped
      Removed value: -{
      -  "description": "With since: matching entries left out for having no date",
      -  "type": "number"
      -}
  2. Changed7 schema fields changedv2.10.0
    • addedInput schema / properties / intent
      Added value: +{
      +  "description": "current separates historical/imported records into historical_matches; history returns historical records among the ranked candidates, not retired entries; any preserves both. No source is checked automatically.",
      +  "enum": [
      +    "any",
      +    "current",
      +    "history"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / neurons
      Added value: +{
      +  "description": "Explicit neuron-id allowlist, applied before ranking and limit; excludes day logs.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "maxItems": 100,
      +  "type": "array"
      +}
    • addedInput schema / properties / project
      Added value: +{
      +  "description": "Registered project id or alias; omitted uses this connection's boot project.",
      +  "type": "string"
      +}
    • addedInput schema / properties / scope
      Added value: +{
      +  "description": "auto prioritizes the current bound project without hiding other matches; project restricts it plus global preferences/lessons; all ignores the connection project. Organization, not access control.",
      +  "enum": [
      +    "auto",
      +    "project",
      +    "all"
      +  ],
      +  "type": "string"
      +}
    • addedOutput schema / properties / excluded_nonhistorical
      Added value: +{
      +  "type": "number"
      +}
    • addedOutput schema / properties / historical_matches
      Added value: +{
      +  "items": {
      +    "additionalProperties": {},
      +    "properties": {},
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / search_scope
      Added value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "mode": {
      +      "type": "string"
      +    },
      +    "neurons": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "project_id": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "mode"
      +  ],
      +  "type": "object"
      +}
  3. Changed11 schema fields changedv2.9.1
    • changedInput schema / properties / since / description
      Previous value: -"Only entries dated on or after this: a day (\"2026-09-01\") or a span back from today (\"7d\", \"2w\", \"3m\"). For \"what changed lately\" and to keep an old telling out. Undated entries cannot prove they are recent: they are left out and counted in undated_skipped."New value: +"Only entries recorded on or after this: a day (\"2026-09-01\") or a span back from today (\"7d\", \"2w\", \"3m\"). For \"what changed lately\" and to keep an old telling out. A later verification does not make an old entry new. Undated entries cannot prove they are recent: they are left out and counted in undated_skipped."
    • addedOutput schema / properties / possibly_stale
      Added value: +{
      +  "description": "Rows whose best entry is past its shelf life since last verified: warning, next_step (what to check before answering), the entry as last_known instead of matching_content, then the rest of a results row plus age_days, last_verified, shelf_life, shelf_inferred",
      +  "items": {
      +    "additionalProperties": {},
      +    "properties": {
      +      "age_days": {
      +        "type": "number"
      +      },
      +      "last_known": {
      +        "type": "string"
      +      },
      +      "last_verified": {
      +        "type": "string"
      +      },
      +      "neuron_id": {
      +        "type": "string"
      +      },
      +      "next_step": {
      +        "type": "string"
      +      },
      +      "shelf_inferred": {
      +        "type": "boolean"
      +      },
      +      "shelf_life": {
      +        "type": "string"
      +      },
      +      "warning": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "warning",
      +      "next_step",
      +      "last_known",
      +      "neuron_id",
      +      "age_days",
      +      "last_verified",
      +      "shelf_life",
      +      "shelf_inferred"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / possibly_stale_count
      Added value: +{
      +  "type": "number"
      +}
    • addedOutput schema / properties / results / items / properties / also_matched / items / properties / by
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / results / items / properties / also_matched / items / properties / origin
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / results / items / properties / also_matched / items / properties / stale_days
      Added value: +{
      +  "type": "number"
      +}
    • addedOutput schema / properties / results / items / properties / by
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / results / items / properties / origin
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / results / items / properties / rank
      Added value: +{
      +  "description": "Position in the ranking, set when some row moved to possibly_stale",
      +  "type": "number"
      +}
    • addedOutput schema / properties / returned / description
      Added value: +"Rows that came back: results plus possibly_stale"
    • addedOutput schema / properties / stale_warning
      Added value: +{
      +  "description": "Set, first, when some row moved to possibly_stale: do not answer with those as current",
      +  "type": "string"
      +}
  4. Changed4 schema fields changedv2.5.1
    • addedInput schema / properties / kind
      Added value: +{
      +  "description": "Only these entry kinds, e.g. [\"error\"] for past mistakes before repeating one, [\"decision\"] for what was agreed and why, [\"debt\"] for what was deferred. Day logs are left out when set.",
      +  "items": {
      +    "enum": [
      +      "fact",
      +      "decision",
      +      "pattern",
      +      "preference",
      +      "error",
      +      "debt",
      +      "map"
      +    ],
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / since
      Added value: +{
      +  "description": "Only entries dated on or after this: a day (\"2026-09-01\") or a span back from today (\"7d\", \"2w\", \"3m\"). For \"what changed lately\" and to keep an old telling out. Undated entries cannot prove they are recent: they are left out and counted in undated_skipped.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / filters
      Added value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "kind": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "since": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
    • addedOutput schema / properties / undated_skipped
      Added value: +{
      +  "description": "With since: matching entries left out for having no date",
      +  "type": "number"
      +}
  5. Changed2 schema fields changedv2.4.0
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • removedOutput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
  6. Changed3 schema fields changedv2.2.0
    • changedInput schema / properties / domain / description
      Previous value: -"Only neurons in this domain (exact match, e.g. \"proyectos-web\")."New value: +"Only neurons in this domain (exact match, e.g. \"proyectos-web\"). Day logs have no domain: sessions_matched is listed regardless."
    • addedOutput schema / properties / sessions_matched
      Added value: +{
      +  "items": {
      +    "additionalProperties": {},
      +    "properties": {},
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / sessions_total
      Added value: +{
      +  "type": "number"
      +}
  7. Changed17 schema fields changedv2.1.0
    • changedInput schema / properties / limit / description
      Previous value: -"Max neurons returned (default 10)."New value: +"Max neurons returned (default 5, ranked; ask for more only when the top five did not answer)."
    • addedInput schema / properties / limit / exclusiveMinimum
      Added value: +0
    • addedInput schema / properties / limit / maximum
      Added value: +9007199254740991
    • changedInput schema / properties / limit / type
      Previous value: -"number"New value: +"integer"
    • addedOutput schema / properties / has_more
      Added value: +{
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / matched_neurons
      Added value: +{
      +  "description": "Neurons with any hit before limit; total_results is what came back",
      +  "type": "number"
      +}
    • changedOutput schema / properties / results / items / properties / also_matched / items / additionalProperties
      Previous value: -falseNew value: +{}
    • addedOutput schema / properties / results / items / properties / also_matched / items / properties / chars
      Added value: +{
      +  "type": "number"
      +}
    • addedOutput schema / properties / results / items / properties / also_matched / items / properties / entry_id
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / results / items / properties / also_matched / items / properties / preview
      Added value: +{
      +  "type": "string"
      +}
    • removedOutput schema / properties / results / items / properties / also_matched / items / properties / text
      Removed value: -{
      -  "type": "string"
      -}
    • changedOutput schema / properties / results / items / properties / also_matched / items / required
      Previous value: -[
      -  "text",
      -  "kind",
      -  "added"
      -]New value: +[
      +  "kind",
      +  "added",
      +  "preview",
      +  "chars"
      +]
    • addedOutput schema / properties / results / items / properties / content_chars
      Added value: +{
      +  "type": "number"
      +}
    • addedOutput schema / properties / results / items / properties / content_truncated
      Added value: +{
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / results / items / properties / entry_id
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / returned
      Added value: +{
      +  "type": "number"
      +}
    • addedOutput schema / properties / truncated
      Added value: +{
      +  "additionalProperties": {},
      +  "properties": {},
      +  "type": "object"
      +}
  8. Changed1 schema field changed
    • addedInput schema / properties / queries
      Added value: +{
      +  "description": "Alternative phrasings of the same question, searched together with query and fused by rank. Use synonyms, the other language and the concrete product name; 2-4 is plenty.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  9. Changed4 schema fields changedv1.14.0
    • changedInput schema / properties / domain / description
      Previous value: -"Filter by domain"New value: +"Only neurons in this domain (exact match, e.g. \"proyectos-web\")."
    • changedInput schema / properties / limit / description
      Previous value: -"Max results (default 10)"New value: +"Max neurons returned (default 10)."
    • changedInput schema / properties / query / description
      Previous value: -"What to search for (e.g., \"Firebase authentication setup\")"New value: +"What to look for, e.g. \"Firebase authentication setup\". Fewer, distinctive terms beat full sentences."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": false,
      +  "properties": {
      +    "hint": {
      +      "type": "string"
      +    },
      +    "query": {
      +      "type": "string"
      +    },
      +    "results": {
      +      "items": {
      +        "additionalProperties": {},
      +        "properties": {
      +          "also_matched": {
      +            "items": {
      +              "additionalProperties": false,
      +              "properties": {
      +                "added": {
      +                  "type": "string"
      +                },
      +                "kind": {
      +                  "type": "string"
      +                },
      +                "text": {
      +                  "type": "string"
      +                }
      +              },
      +              "required": [
      +                "text",
      +                "kind",
      +                "added"
      +              ],
      +              "type": "object"
      +            },
      +            "type": "array"
      +          },
      +          "confidence": {
      +            "enum": [
      +              "strong",
      +              "weak"
      +            ],
      +            "type": "string"
      +          },
      +          "domain": {
      +            "type": "string"
      +          },
      +          "has_map": {
      +            "type": "boolean"
      +          },
      +          "heat": {
      +            "type": "number"
      +          },
      +          "matched_added": {
      +            "type": "string"
      +          },
      +          "matched_kind": {
      +            "type": "string"
      +          },
      +          "matched_terms": {
      +            "type": "number"
      +          },
      +          "matching_content": {
      +            "type": "string"
      +          },
      +          "name": {
      +            "type": "string"
      +          },
      +          "neuron_id": {
      +            "type": "string"
      +          },
      +          "query_terms": {
      +            "type": "number"
      +          },
      +          "relevance_score": {
      +            "type": "number"
      +          }
      +        },
      +        "required": [
      +          "neuron_id",
      +          "name",
      +          "domain",
      +          "relevance_score",
      +          "matching_content",
      +          "heat"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "total_results": {
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "query",
      +    "total_results",
      +    "results",
      +    "hint"
      +  ],
      +  "type": "object"
      +}
  10. First observedv1.4.0

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description nevertheless adds substantial behavioural context the annotations do not: the confidence field is a search match rather than truth and may need verification, stale rows are demoted into possibly_stale as last_known with a next_step, and non-user lines carry origin (team:<space> or miner). This is genuinely useful context beyond the structured fields, so a 3 reflects solid but not exceptional added value.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The key directive is front-loaded in the first two sentences, and every sentence carries information about a complex tool. The style is telegraphic and jargon-heavy ("also_matched too", "absent fields hold their default: temporal current_claim..."), which costs some readability on first pass but wastes no words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a ten-parameter tool with an output schema, the description covers the decision to call it, how to interpret confidence, staleness and provenance, how to follow up via crbro_inspect and crbro_map, and what missing fields default to. An agent has everything needed to call it correctly and to read the results without guessing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all ten inputs, including the enum meanings for scope, kind and intent. The description's added meaning concerns result fields (entry_id, confidence, also_matched, defaults for absent temporal/verification/freshness/provenance), not the inputs, so it does not lift this dimension above the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: a read-only search over everything saved in earlier sessions, returning one row per neuron. The scope is unambiguous. It does not, however, differentiate itself from retrieval-flavoured siblings such as crbro_context or crbro_boot; crbro_inspect and crbro_map are named only as follow-up reads, not as competing choices.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit, proactive trigger: call it BEFORE answering anything about the user, their projects, preferences, decisions or past work, because the answer is usually stored. It also routes conditional follow-ups: use crbro_inspect view=neuron for the full entry, and read crbro_map before touching a system flagged by has_map. Only the when-not case is left implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.