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

Annotations cover the safety profile (readOnly/openWorld/non-destructive), and the description layers on non-obvious behavior: free, rate-limited, cached; per-query error isolation in a batch; candidate handles that expire and must be refreshed; and the limit ≥2 threshold that controls whether preview media is attached. This is materially beyond what annotations or schema convey.

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 the core purpose and batch-vs-single decision, then layered with progressively finer constraints; each sentence carries distinct information. It is on the long side for a search tool, but no sentence is redundant.

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?

Even though an output schema exists, the description still flags the important shape details (candidates, candidateId, attribution, license, preview URL, ordered results[]). Combined with the annotations and rich schema, an agent has everything needed to call this 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 coverage is 100%, so the baseline is 3, but the description adds real semantics: the query-vs-queries[] alternation and batch result ordering, the kind default (video) which the schema does not declare, and the limit ≥2 preview rule. The only untouched fields are minWidth/minHeight/durationSec, which the schema already documents.

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+resource (search licensed stock media) and enumerates the scopes it covers (video, photo, sound effects, GIFs). It explicitly contrasts itself with siblings generate_media and import_resource, so an agent can route to it 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 when-to-use routing: 'reach for this before generate_media when real footage beats synthesis', and directs follow-up to import_resource. It also states a strong preference for the batch form ('strongly prefer the batch when you know several things you need'), which is actionable guidance rather than description.

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