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

Annotations already declare readOnly/idempotent/non-open-world, so safety is covered. The description adds substantive non-annotation context: the curated, license-audited, redistributable nature of the sets, the pinned upstream revisions, and the immutability of returned svg_url values. It does not describe result caps or pagination behavior, keeping it just short of a 5.

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?

Three sentences, front-loaded with the what and constrained how, ending with the follow-up call routing. Dense but each sentence carries distinct information; the provider list is long yet earns its place by clarifying scope.

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, and the description compensates by naming the returned fields (icon ids, styles, aliases, immutable svg_url). With 6 parameters at 33% coverage, some gaps remain around limit/q semantics, but for a filtered search tool the description is close to complete.

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 only 33%, so the description must compensate. It does add real meaning for set, style, and category by enumerating concrete style values (outline, filled, solid, regular) and noting that queries may be Chinese, English, or mixed, but it says nothing about q, limit, or language behavior beyond the enum. Partial compensation only.

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 (Search) over a precisely characterized resource (reviewed, commercially usable SVG icon sets), naming the actual providers (Tabler, Lucide, etc.) and the scoping constraint (pinned to audited upstream revisions). It is clearly distinguishable from the sibling get_ui_icon, which retrieves a single icon's source.

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 explains how to scope a search (by set, style, or category) and explicitly routes the agent to the sibling get_ui_icon for the verbatim SVG source, warning against redrawing or approximating. It lacks an explicit 'when not to use' or a statement of when a broad unfiltered query is appropriate, but the workflow context is clear.

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