Enrich one lead

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

Annotations provide readOnlyHint=true and openWorldHint=true, covering safety and external data scope. The description adds valuable behavioral context: billing details ($0.0067 per found record, not-found refunded), cost guidance (call get_balance, read cost.amount_charged), and the 'prefer id' accuracy note. It does not disclose potential latency for realtime mode (that's in the schema) or failure behavior, but the cost disclosure goes beyond annotations and meaningfully informs the agent.

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?

The description is front-loaded with the core purpose in the first sentence, then cost, then guidance. It is efficient with no filler—every sentence adds functional information. It is slightly longer than necessary due to the billing detail, but that detail is decision-relevant. Structure is logical: purpose → cost → identifier preference → bulk alternative. A 5 would require even tighter phrasing without losing the cost nuance, but this is well above average.

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?

Given the tool has 6 parameters, an output schema, and rich annotations, the description covers the essential context: single-person scope, identifier options, cost behavior, and the bulk alternative. It does not describe the response format, but the presence of an output schema covers that. It also does not explicitly mention the mode escalation behavior (only in the schema), but that is adequately captured in parameter descriptions. For an agent to call this correctly, the description plus schema provides sufficient guidance, with minor gaps in distinguishing from closely related tools like resolve_profile.

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 each of the six parameters is already documented (id, mode, email, compact, timeout_ms, linkedin_url). The description adds the 'prefer id' recommendation and clarifies email is for reverse lookup, but these are marginal additions over the schema. The baseline of 3 is appropriate because the schema carries the primary semantic weight and the description does not need to compensate for missing parameter info.

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?

The description states a clear verb ('enrich') and resource ('one known person') with three precise identifier types (Generect id, LinkedIn URL, work email). It explicitly differentiates from bulk operations by naming start_bulk_job as the alternative for many people, and its phrasing 'Full profile for ONE known person' contrasts with search/preview tools. Purpose is unmistakable and distinct from siblings.

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?

The description gives explicit when-to-use guidance: for a single known person, and when not to use it ('For many people at once use start_bulk_job'). It also advises preferring the id from search/preview for accuracy. It does not enumerate every sibling alternative (e.g., get_lead_by_url, resolve_profile) but the context of 'known person' and the named bulk fallback provide solid direction. A minor gap: it does not explain when to choose this over resolve_profile or get_lead_by_url, but the identifier focus covers most use cases.

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