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

Annotations only cover the generic safety profile (not read-only, not idempotent, not destructive). The description adds material behavioral context they don't: cost (~5.7 credits/minute of range, billed by the second), the shot-change boundary rule that starts new tracks, and a required skill prerequisite. It does not say whether tracks persist in the project or are ephemeral, which is the main remaining gap.

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?

Front-loaded with purpose, then return shape, then required params, then cost and prerequisite – a sensible order with no padding. Slightly dense in the middle run-on listing return fields, but every sentence carries 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?

With no output schema, the description does the work of describing returns (a track id per face, most-seen first, when/where each appears, and a numbered face sheet). Combined with cost, prerequisite, and shot-change behavior, an agent has nearly everything needed; only parameter-level detail (assetId/projectId) is missing.

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 only 20% – just projectId is documented. The description compensates for part of that by clarifying that startTime/endTime are a source-time range and that fps is normally 10, but assetId ('ready video') and projectId semantics are left thin, so a third of the parameters remain murky.

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: 'Find and follow every face in a source-time range of a ready video.' The target (faces, not boxes, detections, or points) cleanly separates it from siblings like track_box, track_detection, track_points, and find_objects without needing schema inspection.

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?

Gives concrete preconditions and usage context: 'Specify startTime, endTime and fps (normally 10)', 'Load builtin-object-tracking first', and the downstream step 'Bind a track with <follow>'. It stops short of naming alternative trackers or when-not-to-use this one, which would be needed for a 5.

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