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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=false and openWorldHint=true. The description adds genuinely useful semantics — that the stored result is labeled agent-reported and is never human approval or independently verified execution — which tells the agent how much trust to place in the record. It leaves the disruptive side implied by destructiveHint completely unexplained (does re-reporting overwrite a prior check?), and says nothing about the idempotency_key despite idempotentHint=false.

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 short sentences with no filler, and the core action is front-loaded. The first sentence duplicates the title verbatim, which is minor redundancy rather than bloat.

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 9-parameter, 7-required mutation tool with a nested object and destructiveHint=true and no output schema, the description covers the trust/labeling semantics well but omits the write-conflict story (expected_version, idempotency_key, overwrite behavior) that an agent most needs before calling it. Enough to call safely in the happy path, not enough for retries or conflicts.

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 coverage is only 44% across 9 parameters, so the description must compensate, and it does partially: 'evidence' and the nested 'fulfillment.discovery' path are given real meaning that the bare schema lacks. It says nothing about 'state' (which drives the pass/fail verdict), 'notes', 'capability' format, or how 'idempotency_key' and 'expected_version' interact on retries or stale writes.

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 first sentence names a specific verb ('Record') and resource (the setup agent's capability assessment), plus the payload notion of evidence and a discovery path. It does not, however, distinguish itself from siblings summer_capability_checks_save or summer_capability_checks_test, which an agent must guess between when deciding how to persist a check.

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?

'A pass needs evidence and a discovery path' is a validity rule about the payload, not a statement of when to call this versus the sibling save/test/get/list tools. There is no explicit when-to-use, when-not-to-use, or named alternative anywhere in the description.

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