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

Annotations already cover read-only, idempotent, non-destructive, closed-world. The description adds genuinely non-obvious behavior: the access-right requirement and the fact that a refusal is returned naming the robot, plus that failures are included in the evidence and each observation carries source, conditions and control mode. It stops short of describing result ordering, volume limits, or what an empty evidence set looks like beyond the 'no evidence found' label.

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?

Two sentences, front-loaded with the core purpose, then the evidence taxonomy and finally the refusal case. The enumerated label list earns its space because it tells the agent how to interpret results.

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 usefully describes the return shape (label per capability plus dated observations with source, conditions, control mode) and the error case. The main remaining gap is robot_id format, which matters for correct invocation.

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?

Only one parameter (robot_id) with 0% schema description coverage, so the description must carry the burden. It implies the parameter identifies the robot to check and governs the access-right check ('naming that robot'), but never states the expected format (ID vs name) or what happens when the ID is unknown — partial compensation only.

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 opens with a specific resource and scope: 'What one robot has actually been seen doing, and the evidence for each capability,' which is far more informative than the title 'Observed capabilities.' It never names a sibling (e.g., hardware_get_robot_signals or get_robot_support) to differentiate itself, so an agent must infer the boundary from the resource alone.

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?

Usage is implied by the resource — call this when you need evidence of what a robot has actually done — and a precondition is stated ('Requires an access right on the robot requested'). However, there is no explicit when-to-use-versus-alternative guidance against the many sibling capability/signal tools.

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