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

Annotations already cover read-only, idempotent, non-destructive, and closed-world behavior, so the description is free to add real value — it discloses the search scope (all sets), the ranked return shape, and a practical coverage limitation about brand logos in Tabler. It does not mention result count/pagination beyond the schema's limit default, but the coverage caveat is genuinely useful context an agent couldn't infer.

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?

Two dense sentences, front-loaded with the action and scope, with the caveat last. The embedded template snippet is slightly noisy but earns its place by showing the exact reference format the agent will receive.

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?

With no output schema, the description compensates by describing the return as ranked refs in a concrete format, and all four parameters are covered by the schema. What remains thin is guidance on result selection (ranking criteria, how many sets are searched), which keeps it from a 5.

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 all four parameters are already documented with examples and an enum, giving a baseline of 3. The description's example ref 'tb/TbPhone' clarifies the set/name output format but adds little about the parameters themselves (q, set, kind, limit) beyond what the schema states.

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 (search) and resource (every icon set) and even describes the return value as ranked refs. It is clearly distinguishable from siblings like find_image and find_video by resource type, though it never names them explicitly.

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?

Usage is implied rather than stated: the brand caveat ('Tabler lacks many brand logos; brands come from fa / si') steers the agent toward the right set/kind but never says when to choose find_icon over find_image or when to fall back to another tool. There are no explicit exclusions or alternative routing.

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