Capture analyst-entered observations, inferences, or unknowns with exact evidence references; stores the assertion without verifying it.
Record an analyst-entered observation, inference or unknown with exact evidence references. This records the assertion and does not independently verify it.
| Name | Required | Description | Default |
|---|---|---|---|
| statement | Yes | ||
| project_id | Yes | ||
| limitations | No | ||
| evidence_ids | Yes | ||
| classification | Yes |
Changes observed during successful MCP inspections.
v0.4.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare a non-destructive, non-idempotent write. The description usefully adds that the record is an unverified assertion, which is genuine behavioral context an agent cannot get from annotations. It says nothing, however, about duplicate handling despite idempotentHint=false, nor whether evidence IDs must pre-exist in the project.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with zero waste; the core action comes first and the non-verification caveat follows as a qualifier. Nothing repeats the schema.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 5-parameter write tool with no output schema and zero schema description coverage, the description is only partially sufficient. It omits the limitations concept, any mention of expected ID formats, and what is returned on success, though the core 'unverified assertion' framing is a good start.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must carry parameter meaning and it only partly does: it enumerates the classification values and explains evidence_ids as 'exact evidence references', and implies statement. The 'limitations' and 'project_id' parameters receive no explanation at all, leaving real gaps at zero schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource (records an analyst-entered observation/inference/unknown) and names the three classification kinds, which makes the tool's scope concrete. It also implicitly distinguishes itself from verification/inspection siblings by saying it 'does not independently verify', though it never names an alternative tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage ('analyst-entered', 'with exact evidence references') but never states when to use this versus read_evidence/list_evidence or a verification path. There is no explicit when-not guidance, so the agent must infer the conditions from the wording.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.