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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds one genuinely non-obvious trait — descendants remain listable at any depth even after the original upload is deleted — but says nothing about ordering, pagination behavior, or how results are limited.

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?

One compact sentence with the default listing mode front-loaded and the optional recursive mode following. No wasted wording, though "available" is a soft qualifier that adds little precision.

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 three-parameter read-only listing tool with no output schema, the definition covers the key scoping concept but never indicates what a "result" contains (id, status, parent linkage) or how pagination interacts with recursive traversal. Adequate to call, not quite enough to predict the response.

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 0%, so the description must carry semantic load. It explains root_upload_id well (optional, selects all descendants of one upload at any depth, survives deletion), but limit and offset are left entirely unexplained — only their conventional names imply pagination, and defaults are visible only in the schema.

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 verb is clear ("List") but the resource is described only as "available results", which does not explicitly say generations or distinguish this from siblings like list_uploads, get_generation, or list_upload_sessions. The clause about descendants of one original upload clarifies the domain somewhat, but the agent must infer that "results" means generated outputs.

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 two modes (flat listing vs. recursive descendant listing via an upload root) but gives no explicit when-to-use guidance, no mention of when to prefer get_generation for a single item, and no prerequisites or exclusions. The mode choice is only hinted at through the optional root parameter.

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