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

Annotations already declare readOnly/idempotent/non-destructive and closed-world, so the trailing "Read-only" is redundant. The description does add value beyond annotations: it discloses the result fields (family, catalog, category, weights) in the absence of an output schema, and states the no-auth/no-workspace_key behavior.

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?

The purpose and scope lead, followed by usage and result shape; every sentence carries information except the redundant "Read-only." Sentence fragments are choppy but the content is dense and non-repetitive.

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 enumerating the returned fields and categories, and it closes the two practical gaps an agent would have: whether a workspace_key is required and where the result value goes next.

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 query/limit/source/category are already documented including defaults, cap, and the enum. The description reinforces that query is a family-name match and adds the downstream contract for the returned family name, but supplies no syntax beyond the schema, matching the baseline-3 expectation.

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) and resource (fonts Blaze can render), names both underlying catalogs (Google Fonts + Blaze licensed catalog), and gives concrete example queries. It also explicitly separates itself from get_brand_kit, which handles brand fonts, so an agent can route correctly without opening a schema.

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 says brand fonts come from get_brand_kit instead, and that a returned family name is passed unchanged into compose_design's font field. It also removes a prerequisite guess by stating no workspace_key is needed.

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