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

Annotations already establish a read-only, closed-world search, so the description's added value is the ranking and exclusion behaviour: results are re-ranked by shape proximity and badly-mismatched frames are silently dropped — an agent must know this to interpret zero results correctly. It also states images are never cropped, which prevents a wrong assumption about post-processing, and that previews are returned. Pagination/limit behaviour is left to the schema, which covers it adequately.

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?

Four tight sentences, each doing distinct work: purpose, query phrasing, shape-targeting behaviour, licensing/framing constraint, return value, and sibling routing. The most decision-relevant content (what to pass, and the exclusion side effect) is front-loaded.

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 9-parameter search with an output schema, annotations, and 78% schema coverage, the description covers what structured fields cannot: natural-language query latitude, the shape-ranking/exclusion side effect, no-crop policy, and tool routing. Return values are sketched ('a preview of each image') without duplicating the output schema.

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 high (78%), so the baseline is 3, but the description adds real semantic value for the two least self-explanatory parameters: target_width/target_height don't just filter, they re-rank and exclude results, and must be supplied as a pair. That meaning is not conveyed by the schema's pixel-dimension descriptions alone.

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 resource — 'Find images for sale by description, mood, colour or subject' — and immediately clarifies that natural-language descriptions are as valid as keywords. It also explicitly distinguishes itself from get_image and list_collections, so an agent can pick the right tool 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?

Names both alternatives and the condition selecting each: get_image when an id is already known, list_collections to browse rather than search. It also gives conditional guidance for target_width/target_height ('when the image is destined for a specific screen'), including the consequence of omitting them.

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