Find Icons

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

Annotations already cover read-only/idempotent/non-destructive, so the description invests in undisclosed behavior instead: the index is keyword-matching, multi-word queries fall back to a per-keyword union, `variant` only re-orders rather than rewrites names, and every returned name is guaranteed to exist. These are exactly the ranking and output-guarantee facts an agent cannot infer from 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?

Front-loaded purpose, then usage ordering, then query-shaping advice, then examples, then the output guarantee. Every sentence carries a distinct decision-relevant fact, and the examples are short and directly reusable.

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?

No output schema exists, yet the description compensates by explaining what comes back (names guaranteed to exist in the library, variant only affects ordering) and what to do with them. Combined with annotations covering the safety profile, nothing material is missing for correct invocation.

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 100%, so the baseline is 3; the description earns extra by specifying query shape ('a single canonical noun', not a phrase), showing why ('home' beats 'home house dwelling'), and clarifying that `variant` affects ordering only. It leaves `libraryId` to the schema, which already says it comes from find-icon-library.

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 resource ('Search for specific icons within an icon library') and immediately distinguishes itself from the sibling find-icon-library, which handles library selection rather than icon selection. An agent knows exactly which of the two to call at each stage.

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 sequences the workflow: 'Use this after find-icon-library', and names the downstream step (pass results to `install-icons` verbatim). It also gives a negative guideline — 'Search once per concept; you don't need to retry with synonyms' — which prevents a common wasteful retry loop.

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