Fetch the ball

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

Annotations only declare the safety profile (readOnly false, destructive true, openWorld false); the description adds substantial operational context: the multi-step motion plan, obstacle avoidance, the known last-~10cm ball-loss failure mode, the recovery path via look(), and STOP as the terminator. This is rich behavioral disclosure well beyond the 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?

Front-loads the core action and sequence before the caveats, and every sentence carries information (process, sibling differentiation, failure mode, termination). It is dense but not padded, though the parenthetical detail about the control panel's map is slightly tangential.

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 characterizes the result state ('can't confirm the ball is held') and the recovery action, and it covers the failure mode and termination. The only real gap is the unexplained speed_percent parameter, which leaves an agent unable to reason about its default.

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% and the single parameter speed_percent (default 40, range 5-100) is never mentioned in the description, so its units, effect on behavior, and safe values are undocumented anywhere. The description fails to compensate for the low coverage.

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 concrete verb+resource (fetch the ball into the kicker) and unpacks the full behavioral sequence: locate, drive to just short of it around obstacles, creep up with the camera. It explicitly distinguishes itself from the sibling approach_object by noting the ball needn't be in view.

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?

Names the alternative (approach_object) and the condition that selects this tool over it — the ball need not be in view. It also prescribes a recovery step (check with look() if the result can't confirm the ball is held) and notes STOP terminates it, though it doesn't state when to prefer approach_object instead.

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