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

The description adds meaningful behavioral context beyond the annotations: it states the operation is idempotent (already in CRM are reported, not duplicated), which aligns with the idempotentHint annotation. It also discloses the automatic company linking behavior and the stage assignment. It doesn't describe the response format, but with no output schema and idempotency covered, this is a solid disclosure.

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?

Three sentences, each earning its place: the action and stage, the company linking behavior, and the idempotency guarantee. No fluff, front-loaded with the core purpose.

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 single-parameter tool with idempotentHint and destructiveHint annotations, the description covers the essential behavioral aspects: what happens, how linking works, and idempotency. It doesn't mention error cases or response details, but given the simplicity and annotation coverage, it is nearly complete. A small gap is not specifying what 'reported' means in the response.

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 0%, so the description must compensate. It explains the purpose of contact_ids implicitly ('saved contacts') but doesn't specify the format of the IDs or where they come from. However, with only one parameter and a clear name, the parameter semantics are adequately inferable. Baseline 3 is appropriate because the description adds some context but not detailed parameter-level guidance.

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 specific verb ('Add'), a specific resource ('saved contacts to the CRM as leads'), and a key distinguishing detail ('without putting them in a campaign (stage prospect)'). It also explains the automatic company linking, which clearly differentiates it from siblings like add_contacts_to_campaign and add_companies_to_crm.

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 when to use this tool: when you want saved contacts as CRM leads at the prospect stage, not in a campaign. It doesn't explicitly name alternatives or exclusions, but the stage clarification and sibling context make the usage context clear. It could be improved by explicitly saying 'use add_contacts_to_campaign to put them in a campaign.'

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