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

Goes well beyond the annotations by disclosing credit economics (1 credit, charged only on a saved value, refunded when status is not_found), the save gate (name match plus verified email on the contact's company domain), and the 30-day already_tried cooldown. It also explains that retrying with the same idempotencyKey returns the first result rather than repeating the action, which is meaningful context despite idempotentHint already being set.

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?

Front-loads the verb and resource in the first sentence and every subsequent sentence adds a distinct constraint (cost, save gate, prerequisites, cooldown, idempotency) with no filler. The style is telegraphic in places ('field is email or linkedin', 'Fills blanks only'), which reads abruptly but remains efficient.

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, open-world lookup with no output schema, the description covers cost, success/failure statuses, prerequisites, and retry semantics, which is most of what an agent needs. It stops short of describing the shape of a successful response beyond 'saves it to that contact'.

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 only 33% schema coverage, the description compensates by naming the id's provenance (getPipeline), enumerating the two field values, and clarifying that the idempotencyKey must be reused only for an identical retry and returns the cached first result. It does not explain the nested body/params wrapping or the uuid format constraint, but the essential meaning of all three parameters is covered.

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 and resource ('looks up one missing work email or LinkedIn profile for a contact already in the pipeline') and narrows it to a single field per call. It also tells the agent where the required id comes from ('by contact id from getPipeline'), which distinguishes it from sibling lookup tools without opening any 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 strong preconditions: it 'fills blanks only', requires a full name plus a company website/work email (or a LinkedIn URL for email), and explains that 'already_tried' means nothing was found in the last 30 days. What it lacks is explicit routing to an alternative tool when the contact is not in the pipeline or the field is already populated, so the agent must infer the fallback.

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