prefer_tool

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

The description extensively discloses behavior: how ambiguity is handled (returning candidates and asking the user), how margin affects ranking, that preferences yield to hard requirements, and that results indicate whether the preference was served or passed over. Since no annotations are provided, this full behavioral disclosure is essential and well done.

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 verbose and repetitive, with confusing sentence structures (e.g., the run-on about 'must_be' compliance). It could be edited down significantly while retaining the same information. The structure is not scannable or well-organized.

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?

While the description provides rich behavioral context (ambiguity resolution, ranking logic, precedence over hard requirements), it lacks details about the expected output format (beyond a mention of 'preferred:' line) and the role of 'project_id'. For a tool with no output schema, these gaps leave some ambiguity for the agent.

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?

The description explains the meaning of 'tool' (user's wording, possibly ambiguous), 'margin' (how far behind the best tool is acceptable), and 'note' (user's wording shown back). However, 'project_id' is never mentioned, and the schema provides no descriptions. Thus, parameter coverage is incomplete.

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 the tool's purpose: to set a preference for a catalog tool so that HyperRoute uses it when acceptable. It also provides example user phrases that trigger the call, making the intent unambiguous.

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 specifies when to call the tool (when the user expresses a preference for a particular tool) and gives concrete examples. It does not explicitly contrast with sibling tools like update_preferred_tool, but the context of the sibling list plus the examples is sufficient for most use cases.

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