prefer_tool

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

With no annotations the description carries the full burden, and it discloses genuinely non-obvious behavior: ambiguity returns `candidates` rather than guessing, the margin scale and its tuning direction, and that a failed must-have still excludes the tool. It omits what a successful call returns or whether an existing preference is replaced, and says nothing about project scoping.

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?

Dense and front-loaded: the serving semantics come first, then parameter notes in a compact order. The telegraphic 'note: their wording' phrasing is slightly cryptic, but no sentence is filler.

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?

There is no output schema and no annotations, so the description is the only source of behavioral detail; it covers the core effect and margin tuning well but leaves `project_id` entirely unexplained and never states the success-side outcome or precedence over existing preferences. Adequate for the main path, incomplete at the edges.

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 0%, so the description must compensate, and it does for three of four parameters: `tool` (user's wording, ambiguity handling), `margin` (default 0.10, 0–1 scale, wider/narrower interpretations) and `note`. `project_id` is never mentioned in either schema or description, which caps the score.

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?

States a specific verb and object ('Favour a catalog tool') plus the exact effect: the tool is served whenever acceptable and within `margin` of the best. It does not explicitly name the siblings it is not (unprefer_tool, my_preferred_tools), so it stops short of a 5, but the verb alone makes the contrast obvious.

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?

Gives a concrete trigger phrase ('I like Kagi, use it when it's acceptable') and an explicit branch for the ambiguous case: return `candidates`, ask the user, never pick. No explicit when-not guidance or named alternatives such as unprefer_tool for removal, so it is clear context rather than full routing.

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