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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false), so the description adds the operational context that matters: cost of 1 profile credit, the requirement of a free StartupHub.ai account, and the full return payload. It stops short of describing failure/fallback behavior when Gravatar or person matching misses, though the 'best available' and 'if person is unknown' phrasing partially covers this.

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 core contract ('Pass an email, get back: ...') followed by return fields, then use cases, then cost/auth. The colon-delimited return list is efficient, but marketing phrasing ('The killer endpoint for...') and the credit-comparison sentence are slightly padded relative to the informational payload.

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?

No output schema exists, and the description compensates by enumerating the returned fields in order of importance, plus auth requirement and per-call cost. For a single-parameter read-only enrichment tool, an agent has everything needed to call it and interpret the result.

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?

One parameter with 0% schema description coverage, so the description carries the burden: 'Pass an email' identifies the input, and the free-provider/local-part discussion implies the expected format (a real address whose domain and local part are parsed). It never spells out format constraints or invalid-input behavior, so it is not fully compensating, but it adds real meaning beyond the bare 'email: string'.

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 (enrich) plus resource (email address) and enumerates exactly what comes back, including name/source, Gravatar profile, mail provider, matched person, startup/investor domain match, name heuristic, and free-provider flag. It explicitly distinguishes itself from the sibling chain get_person_by_email + get_startup_by_domain + get_investor_by_domain, so an agent can pick it without opening other schemas.

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?

Names concrete usage contexts (HubSpot/Salesforce auto-enrichment, Gmail/Outlook plugins, lead-scoring pipelines) and explicitly positions itself against the alternative of chaining three sibling tools, with the cost tradeoff stated (1 credit, cheaper than chaining). It even gives a when-not condition: skip company matching when the free-provider flag fires on consumer addresses.

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