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

Annotations only declare readOnlyHint and openWorldHint, and the description adds genuinely new context: a 3-credit cost per call, free pricing on misses/errors/no-evidence answers, and the implicit caution that results need verification before sending. It does not describe the structure or count of the ranked candidates, which is the one remaining behavioral gap.

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, front-loaded with the core capability before routing rules, cost, and the required input pattern. Every sentence carries distinct information with no repetition of the schema.

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?

With no output schema, the description carries the return-value burden and does so minimally ('returns ranked candidates'), and it fully covers usage routing, cost, and input patterns for a 4-parameter tool. A brief note on how many candidates come back or what a no-evidence result looks like would close the gap.

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 50% (first_name and last_name carry no descriptions), but the description compensates by stating the two input patterns: 'Provide first_name and last_name, or full_name.' That resolves the otherwise undocumented mutual-exclusivity relationship between the three name parameters.

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 ('Finds the most likely work email for a named person at a company domain') plus the return shape ('ranked candidates'). It also explicitly contrasts itself with apione_email_verify and apione_people_search, so an agent can distinguish it from siblings 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 the triggering condition ('when you have a name and a domain and need an address to contact'), names both near-miss alternatives and the conditions that select them, and prescribes a follow-up step ('Check the result with apione_email_verify before sending'). Nothing is left to inference.

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