observation_record

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

With no annotations provided, the description must fully disclose behavioral traits. It mentions that attaching 'loop' and 'phase' 'unlock[s] the next section', implying a side effect beyond recording. However, it does not explain if the tool is idempotent, requires specific permissions, or what the return value looks like. It lacks detail on the nature of the evidence recording (append, overwrite, etc.).

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?

The description is only two sentences long, with the main purpose front-loaded in the first sentence. The second sentence adds critical usage context about the phase gate. No extraneous information is present. Every sentence earns its place.

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?

Given the tool has 6 parameters with no schema descriptions, no output schema, and no annotations, the description partially compensates by explaining the purpose and the phase-gate unlock mechanism. However, it omits details on return values, parameter formats, and error conditions. For a moderately complex tool, this leaves gaps.

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?

The input schema has 6 parameters with 0% description coverage. The description only mentions 'loop' and 'phase' in the context of satisfying the phase gate, but does not explain their types, allowed values, or how they map to schema properties. Parameters like 'kind', 'sourceRef', and 'runId' are entirely undocumented in the description, leaving the agent to rely solely on the schema names.

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?

The description clearly states 'Record lightweight evidence for the current phase', specifying the verb 'Record' and the resource 'evidence'. It also mentions 'what you actually did/observed', which further clarifies the tool's function. This distinguishes it from siblings like 'artifact_record' which likely records artifacts, and 'register_hypotheses' which records hypotheses.

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 indicates when to use the tool: 'for the current phase' and to 'satisfy the phase gate and unlock the next section'. It provides clear context of use, but does not explicitly state when not to use it or mention alternative tools. However, the phase-gate requirement is a strong guideline.

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