Skip to main content
Glama
cirwel

UNITARES

by cirwel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

store_finding

Write a durable finding into the cross-agent knowledge graph and return its discovery_id. Search shared memory first to avoid duplicates; revise existing entries with update_finding.

Instructions

Write one new durable finding into the cross-agent knowledge graph and get back its discovery_id. summary is required at call time even though the schema marks every field optional; severity high or critical is refused unless the session is bound to a registered agent, while low and medium fall back to an anonymous writer id. Every call mints a NEW discovery — search_shared_memory first, and revise one with use_tool(tool_name='update_finding', ...). Use it for a discovery, root cause or correction, and record_result for task, tool or test outcomes; budget 20 findings an hour.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNoTags (action=store, note); for action=search an exact any-of filter in every search mode.
contentNoExtended content/details (for action=store, note, or promote)
detailsNoExtended details for discovery (for action=store or promote). Alias: content
summaryNoDiscovery summary (for action=store or promote)
agent_idNoLeave unset; the bound session is the writer.
severityNoSeverity: low, medium, high, critical (for action=store or action=update)
task_labelNoS22 H5 provenance: human-readable bounded task label
task_outcomeNoS22 H5 provenance: outcome label for the bounded task
comparison_keyNoS22 H5 provenance: stable key for comparing the same bounded task across harnesses
discovery_typeNoaction=store; one of architectural_decision, learning, pattern, bug_fix, refactoring, documentation, experiment, question, note, rule, insight, bug_found, bug, improvement, exploration, observation.
memory_contextNoS22 provenance: memory/KG/transcript surfaces visible to the writer
continuity_tokenNoSame-process rebind proof only; never a cross-process resume.
client_session_idNoBinding id for calls in this process; not a cross-process proof.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv3.1.0
    • changedInput schema / description
      Previous value: -"Parameters for knowledge"New value: +"Knowledge graph parameters."
    • changedInput schema / properties / agent_id / description
      Previous value: -"Filter by agent (for action=get, search; omit when using discovery_id readback)"New value: +"Leave unset; the bound session is the writer."
    • changedInput schema / properties / client_session_id / description
      Previous value: -"In-session binding id from start_session()/identity(); pass it on same-process calls. Not a cross-process proof."New value: +"Binding id for calls in this process; not a cross-process proof."
    • changedInput schema / properties / content / description
      Previous value: -"Extended content/details (for action=store or action=note)"New value: +"Extended content/details (for action=store, note, or promote)"
    • changedInput schema / properties / continuity_token / description
      Previous value: -"Ownership proof from onboard()/identity(), for same-live-process rebinds only. Not a cross-process resume credential."New value: +"Same-process rebind proof only; never a cross-process resume."
    • changedInput schema / properties / details / description
      Previous value: -"Extended details for discovery (for action=store). Alias: content"New value: +"Extended details for discovery (for action=store or promote). Alias: content"
    • changedInput schema / properties / summary / description
      Previous value: -"Discovery summary (for action=store)"New value: +"Discovery summary (for action=store or promote)"
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond annotations: discloses that every call mints a NEW discovery (non-idempotent), a 20-findings/hour budget, the auth gating on high/critical severity, the anonymous-writer fallback for low/medium, and the required-summary quirk that contradicts the schema's all-optional marking. This is exactly the behavioral context an agent needs.

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?

Dense but front-loaded: the core write action and return value come first, followed by constraints in descending priority. Every clause carries information, though the run-on sentence packing auth, fallback, alternatives, and budget is heavier than ideal.

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 13-parameter mutation tool with no output schema, the description covers the return value, auth requirements, rate limits, idempotency behavior, and sibling routing. An agent has everything needed to call it correctly without opening other sources.

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

Parameters4/5

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

Schema description coverage is 100%, so baseline is 3. The description adds real semantics on top: summary is required at call time despite the schema, and agent_id should be left unset because the bound session is the writer. Severity gating is also explained, though per-field syntax details stay in the schema.

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?

States a specific verb and resource ('Write one new durable finding into the cross-agent knowledge graph') plus the return value ('get back its discovery_id'). It clearly distinguishes itself from siblings by naming search_shared_memory, update_finding, and record_result as different operations.

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?

Explicit routing: search_shared_memory first, revise via use_tool(tool_name='update_finding'), and the boundary against record_result ('discovery, root cause or correction' vs 'task, tool or test outcomes'). Both when-to-use and which-alternative are spelled out.

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

Deploy Server

Other Tools