List README drifts

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=true, so the safety profile is covered. The description adds genuinely new behavioral context not in the annotations: a flat 5-credit cost and the presence of size_delta in the output. It stops short of describing pagination limits or error behavior, so a 4 rather than 5.

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 compact, front-loaded sentences with no filler. The core identity comes first, the incremental-feed tactic and sibling reference follow, and cost is stated last as a quick note. Every sentence carries distinct information.

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 read-only list tool with full annotation coverage and 100% schema coverage, the definition supplies cost, the incremental-feed pattern, a sibling alternative, and a hint at the return field. Since there is no output schema, the return shape is only partially characterized (size_delta), so it is nearly but not fully complete.

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 the schema already documents id, limit, offset, and since_ts, giving a baseline of 3. The description earns above baseline by explaining the intended sequencing for since_ts (max commit_ts from a previous call for an incremental feed), which is operational meaning the schema's terse 'rows with commit_ts >= it' does not convey.

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+resource (lists commits that changed a model's README on Hugging Face) and even cites the underlying endpoint GET /models/{id}/drifts. The added 'with size_delta between commits' detail distinguishes the return shape from a generic commit list, so an agent can tell it apart from siblings like get_readme_at or get_timeline.

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?

Explicitly names the alternative ('fetch a version with get_readme_at') and gives a concrete usage pattern: pass since_ts = the max commit_ts from a previous call for an incremental feed. That is a clear when-to-use-routing plus a stateful pagination strategy, leaving little to inference.

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