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

Annotations only say readOnlyHint=false and destructiveHint=false, so the description carries the burden of disclosing side effects. It adds valuable behavioral details: the created deal appears on the Deals view for the whole team, creation requires a person or company, and the tool refuses duplicate open deals while naming the existing deal. This goes well beyond the annotations and the schema's individual field descriptions.

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 compact and front-loaded: purpose and team visibility come first, then the linking/creation logic and duplicate policy, then the return shape. Every sentence contributes either to selecting the tool, passing parameters correctly, or understanding the result. No filler or redundant restatement of the schema.

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 an 11-parameter creation tool with no output schema and minimal annotations, the description covers the essential context: core semantics, duplicate handling, link-vs-new patterns, and return shape ('same shape as a query_deals row'). It could be more complete by describing the created deal row fields or permission requirements, but it points to query_deals for the shape and the schema handles per-parameter defaults.

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 baseline is 3. The description adds cross-parameter semantics not obvious from the schema: 'A deal needs a person or a company (or both)', and explains when to use person_id/company_id versus new_person/new_company. It also gives meaning to allow_duplicate by tying it to the refusal behavior. This is meaningful added value beyond the schema.

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?

Description opens with a specific verb and resource ('Create a deal in the user's CRM pipeline') and clarifies this is how a person or company enters the CRM. It differentiates from the sibling update_deal by explicitly saying to 'update that deal instead' when a duplicate open deal exists. An agent can confidently distinguish create_deal from query_deals and update_deal.

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?

Description gives explicit when-to-use: 'this is how a person or company gets into the CRM.' It also provides clear alternatives: link existing people/companies via query_people/query_companies, or pass new_person/new_company; and if an open deal exists, 'update that deal instead, unless the user wants a second one (then pass allow_duplicate=true).' This leaves no ambiguity about when to call this tool versus update_deal.

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