Skip to main content
Glama

Consolidate the session

crbro_consolidate
Idempotent

Close a memory session by logging its summary, flushing the index, recalculating heat, linking new neurons, and syncing team spaces so session knowledge persists.

Instructions

Write: close the session — the only way to log one; call it before the conversation ends, or the session's knowledge is lost. Logs the summary (credentials stripped), flushes the index, recalculates heat, links the neurons written this session and syncs team spaces (offline is normal). Returns session_id, facts_saved, decisions_saved, topics_touched and sync state; promotion_candidates: own lessons found in 2+ project neurons, with a suggested_target (nothing moves). Mid-session open items go to crbro_context; housekeeping, crbro_maintenance.

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": {
      "summary": "<summary>"
    },
    "name": "crbro_consolidate"
  }
}

Input Schema

NameRequiredDescriptionDefault
summaryYesA headline paragraph, not a report: what was done, decided and left open. Facts go to crbro_learn, where recall finds them as facts; this is narrative.
topics_touchedNoNeuron ids used without writing (recalled, inspected); unknown ids go to topics_unknown.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.12.0
    • changedInput schema / properties / summary / description
      Previous value: -"A headline paragraph, not a report: what was done, decided and left open, in a few sentences. The facts themselves belong in crbro_learn, where recall finds them; this text is re-read at every boot. Stored whole, after credential redaction, and searchable by recall as a session hit (sessions_matched). Facts still belong in crbro_learn: a hit in a log is narrative, a fact answers."New value: +"A headline paragraph, not a report: what was done, decided and left open. Facts go to crbro_learn, where recall finds them as facts; this is narrative."
    • changedInput schema / properties / topics_touched / description
      Previous value: -"Neuron ids this session used WITHOUT writing (recalled, inspected, discussed). Added to the log's topics_touched next to the ids written this session; write counters stay real. Unknown ids are dropped and listed in topics_unknown."New value: +"Neuron ids used without writing (recalled, inspected); unknown ids go to topics_unknown."
  2. Changed1 schema field changedv2.4.0
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
  3. Changed1 schema field changedv2.2.0
    • changedInput schema / properties / summary / description
      Previous value: -"A headline paragraph, not a report: what was done, decided and left open, in a few sentences. The facts themselves belong in crbro_learn, where recall finds them; this text is re-read at every boot. Stored whole, after credential redaction. Session logs are not searched by recall: what only lives here is invisible to it."New value: +"A headline paragraph, not a report: what was done, decided and left open, in a few sentences. The facts themselves belong in crbro_learn, where recall finds them; this text is re-read at every boot. Stored whole, after credential redaction, and searchable by recall as a session hit (sessions_matched). Facts still belong in crbro_learn: a hit in a log is narrative, a fact answers."
  4. Changed1 schema field changedv2.1.2
    • changedInput schema / properties / summary / description
      Previous value: -"A headline paragraph, not a report: what was done, decided and left open, in a few sentences. The facts themselves belong in crbro_learn, where recall finds them; this text is re-read at every boot. Stored after credential redaction; beyond 3,000 characters it is cut and the response says so."New value: +"A headline paragraph, not a report: what was done, decided and left open, in a few sentences. The facts themselves belong in crbro_learn, where recall finds them; this text is re-read at every boot. Stored whole, after credential redaction. Session logs are not searched by recall: what only lives here is invisible to it."
  5. Changed1 schema field changedv2.1.0
    • changedInput schema / properties / summary / description
      Previous value: -"What was accomplished: concrete work, decisions, outcomes. Stored (after credential redaction) as the session log later sessions read."New value: +"A headline paragraph, not a report: what was done, decided and left open, in a few sentences. The facts themselves belong in crbro_learn, where recall finds them; this text is re-read at every boot. Stored after credential redaction; beyond 3,000 characters it is cut and the response says so."
  6. Changed2 schema fields changedv2.0.0
    • changedInput schema / properties / summary / description
      Previous value: -"What was accomplished: concrete work, decisions, outcomes. Stored verbatim as the session log later sessions read."New value: +"What was accomplished: concrete work, decisions, outcomes. Stored (after credential redaction) as the session log later sessions read."
    • addedInput schema / properties / topics_touched
      Added value: +{
      +  "description": "Neuron ids this session used WITHOUT writing (recalled, inspected, discussed). Added to the log's topics_touched next to the ids written this session; write counters stay real. Unknown ids are dropped and listed in topics_unknown.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  7. Changed1 schema field changedv1.14.0
    • changedInput schema / properties / summary / description
      Previous value: -"Summary of the session being consolidated"New value: +"What was accomplished: concrete work, decisions, outcomes. Stored verbatim as the session log later sessions read."
  8. First observedv1.4.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already flag this as a non-destructive, idempotent, open-world write, and the description adds substantial context on top: summary logging with credentials stripped, index flush, heat recalculation, neuron linking, team-space sync, and that offline sync is normal rather than a failure. It also enumerates returned fields and explains that promotion_candidates are suggestions where "nothing moves." The only remaining gap is that "knowledge is lost" is asserted without saying what recovery, if any, exists.

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?

Front-loaded with the operative verb and the critical deadline, then the mechanics, then return values, then sibling routing — a sensible order. The sentences are dense and long, and the purpose paragraph compresses several distinct behaviors into one clause chain, but nothing is genuinely filler.

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?

With no output schema, the description compensates by naming the return fields and explaining promotion_candidates semantics. For a two-parameter session-closing write with annotations already covering the safety profile, an agent has everything needed to call it at the right moment and interpret the result.

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 coverage is 100% and the schema's own summary description already carries the "headline paragraph, not a report" and "facts go to crbro_learn" guidance, so the description largely repeats it. The one genuine addition is that credentials are stripped from the logged summary. Baseline 3 applies since the schema does the heavy lifting.

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

Purpose5/5

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

"Write: close the session — the only way to log one" gives a specific verb and resource and explicitly distinguishes this from siblings that only read or maintain. The first word tells an agent the operation is a write, setting it apart from recall/inspect tools.

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?

States the firing condition explicitly ("call it before the conversation ends, or the session's knowledge is lost") and routes other cases away: mid-session open items go to crbro_context, housekeeping to crbro_maintenance. Both the when and the when-not are covered.

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