Search stock photos

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safe/read-only nature is covered. The description adds value beyond annotations by disclosing the API key requirement (UNSPLASH_ACCESS_KEY or PEXELS_API_KEY) and the output shape (URLs and attribution). It does not mention rate limits, but given the annotations cover safety, this extra context is meaningful and earns a 4.

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 sentences, all essential: the function and output, the downstream usage, and the prerequisite. The most important information (search scope and result type) is front-loaded. No redundancy or filler. The structure is efficient and easy to parse.

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?

The tool has four parameters, two enums, and no output schema. The description compensates by stating the output includes candidate URLs and required attribution, and names the specific fields (download_url, attribution) to pass downstream. It does not explain edge cases like no results or error behavior, nor the exact result object structure, but for a search-and-return-list tool this is reasonably complete. It loses one point for omitting error/pagination context, but it covers the critical workflow.

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 100%, so each parameter (query, per_page, provider, orientation) is already well-documented with type, defaults, and enums. The description does not add any additional parameter-level guidance beyond what the schema provides. It introduces the non-parameter terms download_url and attribution, but those are output fields, not parameter clarifications. Per the baseline rule for full schema coverage, a score of 3 is appropriate.

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?

The description clearly states the tool searches Unsplash or Pexels for royalty-free photos and returns candidate image URLs with attribution. The verb 'search' and specific resources are named, and the downstream workflow to create_media distinguishes it from sibling tools like list_media or search_site. It fully clarifies what the tool accomplishes and how it fits the media workflow.

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 gives explicit guidance on when to use it: to find stock photos, and how to use results (pass download_url and attribution to create_media). It also states the prerequisite of API keys being set. It does not explicitly exclude scenarios (e.g., 'use list_media if you already have media'), but the workflow is clear and actionable. Minor gap but strong enough for a 4.

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