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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description is free to add real behavioral detail — fuzzy/typo-tolerant matching, semantic embedding search, and result ordering with best matches first. It doesn't state what happens on zero results or whether matching is scored, but it adds genuine context beyond the annotations.

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 sentences, front-loaded with the action, then the matching mechanisms, then the result ordering. No filler, and every clause carries information an agent would otherwise have to guess.

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 a three-parameter read-only search with full schema coverage and no output schema, the description covers input semantics and result ordering adequately. The remaining gap is navigational: it never relates itself to get_icon, get_community_icon, or list_categories, which matters given five siblings in this space.

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 does enrich the query parameter by explaining what kinds of input match (labels, synonyms, slang, abbreviations, plain-language needs) and that typos are tolerated, which goes beyond the schema's example-based wording, but it says nothing about limit or category behavior.

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?

Opens with a specific verb+resource ("Find icons") and then qualifies the matching strategy (labels, synonyms, UI slang, abbreviations, embeddings, typo tolerance). This clearly separates it from a direct-fetch sibling like get_icon, though no sibling is named 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 only implied: the description tells you it searches by name or meaning, so an agent can infer this is the discovery entry point. There is no explicit when-to-use/when-not, no mention of preferring get_icon once an identifier is known, and no pointer to list_categories for browsing by category (that hint lives only in the schema).

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