Fit the ground frame

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

Explains that the tool writes/persists to scene metrics and that dry_run=true computes without persisting, adding meaningful behavioral context beyond the destructiveHint annotation. It does not mention auth or rate limits, but the non-destructive profile is already covered by annotations.

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?

Single sentence, front-loaded with the action, then endpoint and dry_run behavior. Every part earns its place with no filler.

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 two-parameter tool with no output schema, the description covers the action, effect, persistence switch, and endpoint. Minor gaps are the exact return value and which scene metrics fields are updated, but the calling contract is largely 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 0%, so the description must compensate. It clearly explains dry_run semantics ('computes without persisting'), but leaves scan_id entirely to the schema and name; scan_id is obvious from context but not documented.

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: '(Re)fit the floor plane' and 'write the result onto the scene metrics (POST /ground_frame)'. This distinguishes from read-oriented siblings like scene_ground_frame, but does not explicitly name any alternative.

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?

Clearly implies the tool is for fitting the floor plane and mentions the dry_run mode for computing without persisting, but gives no explicit when-to-use guidance or exclusions relative to scene_ground_frame or scene_planes.

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