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

Annotations already declare readOnly, non-destructive, idempotent and openWorld, so the safety profile is covered. The description still adds real context beyond that: results are preview metadata plus 'import inputs', i.e. a discovery step that hands off to an import, and no design state is mutated.

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?

Two sentences, zero filler, with the core action front-loaded before the negative scoping clause. Nothing is wasted.

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?

An output schema exists, so return values need no explanation, and annotations handle safety. However, with five parameters at 20% coverage, the agent is left guessing about provider differences and pagination semantics, which the description could have closed cheaply.

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 only 20% — only orientation is documented. The description says nothing about query syntax, what provider selection changes, or how page/perPage interact, so it fails to compensate for the four undocumented parameters.

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 (searches) plus resource (stock photos) and names the two external providers, Pexels and Unsplash. The second sentence explicitly excludes the adjacent operations (upload / design modification), which separates it cleanly from the sibling import_stock_photo.

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?

'Does not upload a photo or modify a design' functions as an explicit when-not, telling the agent this is discovery only. It stops short of naming import_stock_photo as the follow-up step, so the routing is implied rather than stated.

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