Classify Contact

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

Annotations already indicate readOnlyHint=false (mutation), destructiveHint=false (not destructive), and openWorldHint=false (closed world). The description adds transparency by stating that classification won't lose transactions or links, which is valuable behavioral context for a mutation tool. It also mentions cost and API key requirement, which are beyond annotations. No contradiction found.

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 a single well-structured sentence that front-loads the core action and critical safety guarantee. The cost and authentication requirements are appended parenthetically without clutter. There is zero waste.

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?

The description, combined with the annotations and output schema, covers most of what an agent needs: it's a safe mutation, it won't lose data, it requires an API key and costs $0.10. The only missing context is clarification on parameter usage (e.g., how entity_id vs person_id are used, what confidence means), but with an output schema present and the safety profile clear, the description is largely complete.

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 only 25% (only request_id and idempotency_key have descriptions), so the description must compensate for the other 6 parameters. The description only explains entity_type's role, but doesn't clarify source, entity_id, person_id, confidence, identity_status, or the relationship between request_id and idempotency_key. While some parameters (like entity_id, person_id) may be self-explanatory, the description doesn't add significant semantic value beyond what's in the schema. Baseline 3 is appropriate, but it could be higher if it explained parameter interplay.

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 clearly states that this tool sets entity_type on a CRM row, with a specific list of allowed values (person/company/merchant/…). It differentiates from similar tools like convert_contact_entity and update_person_identity by focusing on entity_type classification without losing transactions or links. However, it doesn't explicitly name these siblings, so while purpose is clear, sibling differentiation is not explicit.

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 implies use for classifying a contact's entity type, and the emphasis on 'without losing transactions or links' suggests it's the safe alternative to destructive or lossy operations. However, there is no explicit when-to-use/when-not-to-use guidance or direct mention of alternatives. An agent would need to infer when this tool is preferred over others like convert_contact_entity.

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