Check Operation Capacity

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

Annotations already cover the safety profile (readOnlyHint true, destructiveHint false), and the description adds genuinely non-obvious context: it is advisory only, is 'never a reservation or guaranteed price', and unlock estimates additionally require campaigns:read scope. That is real value beyond the annotations, though it says nothing about what the response contains or how a 'no capacity' result is signaled.

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 core purpose and then the advisory caveat. Dense but every clause (variant list, roster limit, scope requirement, no-reservation caveat) carries information; no filler.

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 complex union-typed input with zero schema descriptions and no output schema, the description should also indicate what a result looks like (remaining capacity, boolean fit, denial reasons). It covers the inputs and the advisory caveat well but leaves the return contract entirely unstated.

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% on a single deeply-nested oneOf parameter, so the description must carry the load. It does map the operation variants in prose and states the 1–500 unique roster ID constraint, but it omits the required campaign_id on the unlock path, the count-vs-campaign_creators target discriminator, and the exact operation discriminator strings.

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+resource (advisory capacity check) and enumerates the four things it can check: import row count, saved-creator count, one campaign, and email unlock. An agent knows exactly what question the tool answers, though it never names a sibling or notes what it is NOT (e.g. that it does not perform the operation).

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?

'Advisory check' plus the four operation variants implies pre-flight/pre-creation usage, but the description never says explicitly when to call it versus proceeding directly, nor does it point at alternatives like check_bulk_email_readiness. Usage is inferable but not stated.

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