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

Beyond the annotations (which already flag this as a destructive, non-idempotent, open-world write), the description adds genuinely useful behavioral context: the record is labeled as agent-reported and is 'never human approval or independently verified execution.' That provenance guardrail is something no annotation conveys. It does not explain the destructive/overwrite behavior or the version-conflict handling, so it stops short of a 5.

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?

Three tight sentences, front-loaded with the action and its payload, followed by the validation rule and the provenance caveat. No filler, though the opening sentence largely restates the title verbatim.

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?

This is a complex tool: 9 parameters, 7 required, a nested object, enums, and no output schema, yet the description ignores the optimistic-concurrency contract (expected_version) and the idempotency_key retry semantics documented only in the schema. For a mutation with this much surface area, the description leaves important calling behavior unexplained.

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 only 44% across 9 parameters, so the description must carry more of the load than it does. It only touches 'evidence' and 'discovery' (via the pass requirement), saying nothing about company, environment, capability, expected_version, state, notes or the fulfillment.kind enum.

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 names a specific verb ('Record') and resource (the setup agent's capability assessment), plus the two payload elements that matter (evidence and discovery path). It is clear on its own, but never explicitly distinguishes itself from the very similar sibling summer_capability_checks_save, leaving the agent to guess which of the two writing tools to call.

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?

There is no statement of when to use this versus summer_capability_checks_save, _get, _list or _test. The only guidance is an internal validation rule ('A pass needs evidence and a discovery path'), which constrains the payload rather than telling the agent when this tool is the right choice.

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