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

Annotations already declare readOnlyHint=true and destructiveHint=false, which the description does not contradict. The description adds behavioral context beyond the annotations by noting 'newest first' ordering and explaining the upload workflow, including the fact that connectors cannot send bytes and the r2Path is obtained here. This extra detail is valuable for understanding how the tool behaves in a broader workflow.

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?

The description is two sentences, front-loaded with the primary purpose and ordering, followed by a necessary clarification about uploads. No words are wasted, and each sentence earns its place. It is concise yet informative, making it easy for an agent to parse quickly.

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 simple list tool with two parameters and no output schema, the description is nearly complete. It explains the two modes (generations vs uploads) and the specific upload workflow. The only minor gap is not mentioning that results are paginated or how to adjust the limit, but the schema provides the limit details and the tool's behavior is predictable. Overall, it is well-suited for the tool's complexity.

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?

The schema already describes the 'type' parameter with an enum and a description, but the tool description adds richer meaning to the 'uploads' value, explaining that it lists the user's own source photos rather than generations and when to use it. The 'limit' parameter has no schema description, but its constraints (default 20, max 50, min 1) are self-explanatory. The description compensates for the schema's partial coverage by expanding on the key parameter.

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's purpose: 'List the user's recent generations, or with type "uploads" their own uploaded source photos, newest first.' It uses a specific verb ('list') and resource ('generations'/'uploads'), and the enum in the schema further clarifies the three possible types. This distinguishes it from sibling tools that generate or edit media, as it is purely a listing operation.

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 provides clear context for when to use the 'uploads' type: 'Uploads are the way in when the photo is a local file: connectors cannot send bytes, so the user adds it at https://pixly.app/app and you pick up the r2Path here.' This explains a specific use case and workflow, though it does not explicitly name alternatives or exclusions among the sibling tools. It gives enough guidance for an agent to decide when to call this tool.

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