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

Annotations cover the safety profile (destructiveHint=false, openWorldHint=false), lowering the burden. The description usefully adds the return shape ('numbered detections and an image') and default values, but doesn't disclose permissions, cost, or why readOnlyHint is false for what looks like a read/detect operation.

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 short, front-loaded sentences with no waste; the primary action comes first, followed by output then defaults. Tight and readable.

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 6-parameter tool with no output schema and low schema coverage, the description covers the return value and a prerequisite, but leaves most parameters unexplained. Adequate but with clear gaps for an agent to invoke correctly.

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 coverage is only 17% (just projectId), so the description must compensate for 6 required params. It mentions threshold 0.15 and maxResults 8 only as defaults, and says nothing about assetId, queries, or the 'at' frame semantics, leaving most parameters undocumented.

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 gives a specific verb and resource: 'Find named objects on a source frame', which is clearly distinct from pure tracking siblings like track_box or track_detection. It also states the output (numbered detections + image), but doesn't explicitly name which sibling it competes with.

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?

'Load builtin-object-tracking first' provides a prerequisite/workflow hint, which is genuine usage guidance. However, it never says when to prefer find_objects over track_detection, track_box, or detect_scenes, so alternatives are left to inference.

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