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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds one genuinely useful disclosure — 'Sample data is deliberately not returned' — which prevents an agent from concluding data is missing, but it says nothing about ordering, pagination, or what an empty result means during polling.

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 tightly packed sentences: what it returns first, the notable exclusion second, the usage routing last. No filler and the most decision-relevant content is front-loaded.

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?

With no output schema, the description carries the burden of describing the return shape and does so field-by-field, including the non-obvious visibility/gap metrics. Combined with the polling guidance, an agent has enough to call it and interpret the result without further tools.

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 token, projectId and clipId are already fully documented in the schema itself. The description adds no extra parameter meaning — no default behavior for omitting clipId, no notes on what the token scopes — so the baseline of 3 applies.

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 and resource ('Lists face-tracking runs') and enumerates exactly what comes back per face: faceId, name, frame range, visible-frame count, gap count. That field list plus the explicit 'pick a faceId for bind_face' framing separates it cleanly from track_faces (which starts runs) and bind_face (which consumes ids).

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?

'Use this to poll a queued run and to pick a faceId for bind_face' gives two concrete contexts and names the downstream tool that consumes the result. It stops short of naming the initiating tool (track_faces) or stating when not to use it, so it is clear context rather than full when/when-not routing.

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