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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description layers on the things annotations cannot express: the 403 on free plans, the exact credit model (1 credit on a hit, +8 only for mobile, 0 on no match), that nothing is cached, that the key is the caller's own licence, and the async webhook limitation on phone reveal. Unusually rich disclosure for a read-only tool.

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-loaded with the gating constraint (paid plan), then identifiers, then BYOK/cost mechanics, then the unsupported capability, then an example. Dense and largely waste-free, though the credit-cost sentence is heavy and some clauses could be tightened.

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 9-parameter, no-output-schema tool with plan gating, BYOK auth, and credit implications, the description covers everything an agent needs before calling: prerequisites, accepted inputs, cost, and the one thing that will silently not work (phone reveal).

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 100%, so baseline is 3, but the description adds real semantics beyond the schema: which identifier combinations are alternatives, that the _apiKey is a bring-your-own-key whose results come from the caller's own Apollo entitlement, and a worked example call. It does not touch reveal_personal_emails beyond the phone caveat, keeping it from a 5.

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 ('Enrich one specific person') plus the accepted identifier forms and the fields returned (title, seniority, department, employer, work email). This clearly separates it from siblings like apollo_search_people (find people) and apollo_enrich_organization (enrich a company).

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 usage context: paid plan required (free plan returns 403), the three lookup keys, BYOK requirement, and an explicit when-not ('NOT implemented: phone-number reveal'). It never names the sibling an agent should use instead when the person is unknown (e.g. apollo_search_people), so it falls just short of the top band.

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