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

Annotations already declare mutation (readOnlyHint=false), non-destructive, and open-world (external Pexels fetch), so the safety profile is covered. The description adds a genuinely useful obligation beyond that: the returned credit line must be displayed near the photo or in the footer — an attribution requirement the agent could not infer. It does not disclose whether an existing file at "path" is overwritten or how the image is stored.

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 compact sentences, front-loaded with the action and input provenance before the post-call instruction. Every clause carries information; only minor gain would come from a firmer structural split between action and follow-up.

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 small mutation tool with no output schema and four parameters, the definition covers the source of the photo and the required follow-up attribution. It leaves out overwrite/duplication behavior, the meaning of "size", and where the file actually lands, which matter for an agent that will call this repeatedly on a site.

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 50% and the description compensates for the key undocumented parameter by explaining that photo_id comes from search_images. It says nothing about "size" (enum with a default but no description) or about the relationship between "path" and "site" — i.e., whether path is relative to the site root. Partial compensation justifies a middle score.

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?

"Save a Pexels photo ... into the site" gives a concrete verb and a clearly-bounded resource, and the parenthetical "(id from search_images)" identifies the required input's origin. It is distinguishable from upload_asset by the Pexels/stock-photo framing, though the contrast is implied rather than stated.

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 description implies the ordering: obtain an id from search_images first, then add the photo, then place the returned credit line. There is no explicit when-not guidance (e.g., when to use upload_asset for a local file instead, or whether re-adding the same photo duplicates it).

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