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

Annotations already declare readOnly/idempotent/non-destructive, so the description's added value is in disclosure of output shape: one best-match SVG per query, embeddable inline, inheriting currentColor and CSS scaling. These are real behavioral facts not in the schema. It omits what happens when a query has no match, which is the main remaining unknown.

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 short sentences, front-loaded with purpose then return value then styling behavior, then usage contexts. No filler and nothing buried.

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 single-parameter read tool with no output schema, the description covers what comes back, how to embed it, and how styling is inherited — everything an agent needs to call it and use the result correctly.

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%, including max of 10 and concrete name examples, so the parameter is fully documented structurally. The description only echoes the array semantics via "best match per query" and adds no naming or formatting conventions beyond the schema.

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 SVG icons by name") and describes the exact return payload ("inline SVG markup for the best match per query"). This clearly separates it from generate_image or upload_asset, though it never names a sibling alternative 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?

Gives concrete placement contexts — "buttons, feature lists, navigation, contact rows" — so the agent knows when the tool is appropriate. It stops short of any when-not guidance, e.g. it never says to use generate_image instead when a custom raster image is needed.

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