createLeadMatch

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

Annotations already indicate `readOnlyHint=false` (write operation). The description adds critical behavioral context: 'Writes live data', warns of double-billing if duplicate pair is created, explains that server does not enforce uniqueness on `(lead_id, user_id)`, and instructs on a client-side pre-check. No contradictions with annotations. This rich disclosure goes well beyond the structured fields.

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 well-structured with clear sections (purpose, use when, required, pre-check, parameter interactions, see also). It is front-loaded with the core purpose. However, it is dense and somewhat verbose, with the pre-check section being particularly lengthy. It could be trimmed slightly without losing value, but it maintains good organization.

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 tool with 15 parameters, 6 required, and significant side effects (double-billing, duplicate rows), the description covers all essential aspects: purpose, usage context, pre-duplication check, parameter interactions, and sibling references. No output schema exists, but the description sufficiently explains the behavior and necessary preconditions.

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 only 7% (only `lead_status` has enum description). The description compensates by listing and explaining the 6 required parameters and mentioning scoring fields (`match_price`, `lead_points`, `lead_rating`, `lead_distance`). It also clarifies interactions like 'lead_id and user_id must both exist'. While not every optional parameter is described, the coverage of critical ones is strong, earning a 4.

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?

Clearly states it creates a new leadmatch record and distinguishes from the auto-matching sibling `matchLead`. The verb 'create' and resource 'lead match' are specific and unambiguous. Additionally, it references `updateLeadMatch` as a related tool, further differentiating its purpose.

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?

Explicitly states when to use ('manually creating a lead↔member match BYPASSING BD's auto-matching') and when not to ('usually `matchLead` handles this automatically'). Provides concrete scenarios (data migrations, manual overrides, replaying matches) and a detailed pre-check pattern to avoid duplication. This is exemplary usage guidance.

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