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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=true and idempotentHint=false, so the safety profile is covered. The description adds real value beyond that: it states the return payload (relative path and photographer attribution) and that attribution is persisted into asset metadata, which is not derivable from annotations. It stops short of saying what happens on repeated imports or whether storage quota applies.

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?

Three short sentences, front-loaded with the action and its scope, followed by the exclusion and one non-obvious behavioral fact. No filler and nothing repeated from the schema or annotations.

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 not be spelled out, and the annotations cover the mutation profile. The description adds the key side effect (asset written to project storage, not applied to a design) and attribution persistence. The only real gap is the origin/format of importInput, which is left entirely to the 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 description coverage is only 33%, so the description needs to carry parameter meaning and does not. It never explains projectId, and it does not clarify that importInput is an opaque passthrough object taken verbatim from a search_stock_photos result — that critical detail lives only in the nested schema description. The mention of "Pexels or Unsplash" merely restates the provider enum.

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 and resource ("Imports a selected Pexels or Unsplash photo into project storage") and scopes it further by saying it "Does not apply the image to a design." It is clear what the tool does, though it never names the upstream sibling (search_stock_photos) that produces the importInput, so the differentiation is by scope rather than by sibling name.

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?

The exclusion "Does not apply the image to a design" gives one useful when-not signal, implying a separate apply/placement step. However, there is no positive routing guidance (e.g., "use after search_stock_photos" or "use upload_asset for local files"), so the agent must infer the workflow from the schema.

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