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

Adds substantial context beyond the annotations: tier requirement (Startup or higher), dual consent (read and write), mandatory stable idempotency key, exact-intent confirmation, and optimistic-concurrency discipline ('use its current revision when changing an existing record'). The destructiveHint is already declared, and the description reinforces the write/mutation profile rather than contradicting it.

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 purpose then prerequisites then the state-read caveat. Dense but no filler; each sentence carries distinct information.

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?

An output schema exists so return values need no explanation, and the description covers auth, idempotency, confirmation, and concurrency. It could say more about what the 'bounded snapshot' refresh destroys or invalidates, given destructiveHint=true, but overall it is complete enough to call correctly.

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?

With 0% schema description coverage the description must compensate, and it does: it explains idempotency_key ('stable idempotency key'), confirmation_token ('exact-intent confirmation'), and expected_version ('use its current revision'). It leaves close_id and project_id unexplained, which is a minor gap for a 4-param tool.

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 (Refresh) plus the exact resource and scope ('the close's bounded source snapshot'), and distinguishes itself from the nearby review_evidence/refresh_room siblings by describing the post-refresh review step. An agent can tell what this does without opening the schema.

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?

Gives clear triggering context ('after underlying company records change') and the follow-on action ('Review refreshed exceptions before approval'). It does not, however, name an alternative tool or state when *not* to refresh, so it stops short of full when/when-not guidance.

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