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

Annotations already establish read-only, idempotent, non-destructive behavior, yet the description adds substantive context: searching is free and consumes no downloads, some semantic searches return a pending state with retry_after_seconds, previews grant no usage rights, and downloads require a verified account with per-type licensing (brands vs 3D game asset licence at license_url). This is behavior an agent cannot infer from 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?

Front-loaded with purpose and the search_images exclusion, then procedural details, then licensing — a sensible order with little waste. The licensing sentence is long and packs several conditions into one clause, slightly straining readability, but every sentence carries actionable content.

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 3-parameter search tool with no output schema, the description covers everything needed to call it correctly: what is searchable, how to browse, what pending responses mean and how to retry, and what to do after selection. No critical gap remains for an agent.

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% (only 'query' documented), so the description must compensate: its first sentence effectively enumerates and gives meaning to all six enum values of 'type', and 'Omit query to browse' adds behavior for the optional query. The 'limit' parameter is never mentioned, leaving one gap.

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 and enumerated resource set ('Find published SVG illustrations, coordinated SVG packs, brand logos, sound effects, low-poly 3D game models or videos'), and immediately names the sibling it is not: 'Use search_images for photographs.' An agent can distinguish it from search_images/download_images 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?

Gives explicit routing to the alternative ('search_images for photographs'), an edge-case instruction ('Omit query to browse'), a retry protocol for pending results with the constraint not to change the query while waiting, and a clear handoff to download_asset for each chosen id. When and when-not are both covered.

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