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

Annotations declare destructiveHint=true and idempotentHint=true, and the description earns credit for explaining the credit lifecycle that the annotations cannot: reservation under a cap, consumption on continue/warning/block, release on error, and the feed-credit exclusion. It does not explain what artifact or state is actually created (a check id?) or how long a reservation persists.

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?

Four short sentences, action and billing consequence front-loaded, no filler. The telegraphic phrasing ('Completed continue/warning/block consumes one') is dense but readable and every clause carries 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?

For a mutating, credit-consuming tool with no output schema, the description covers cost and failure semantics well but omits the return value entirely — an agent cannot tell whether it receives a check identifier needed to call get_quality_check later. Billing and idempotency are covered; the response contract is not.

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 carries the full burden. It adds real meaning by tying the two parameters to retry behaviour ('Reuse this quote/key on retries'), implying a fresh key for a new attempt, but it says nothing about quote_id format, provenance, or expiry, leaving half the parameter contract undocumented.

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 action and object: authorize a quoted full-file preflight and reserve one QUALITY credit. The word 'quoted' implicitly links it to quote_quality_check and separates it from get_quality_check, though the jargon 'preflight' and 'QUALITY credit' is not defined anywhere in the description.

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?

Implies the precondition that a quote must exist first, and gives retry guidance ('Reuse this quote/key on retries') plus a funding exclusion ('Feed credits cannot fund this'). It never explicitly names an alternative or states when not to call this instead of quote_quality_check or get_quality_check, so the routing is left partly to inference.

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