Approach an object

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

Annotations only declare readOnlyHint=false and destructiveHint=true; the description adds substantial context they do not cover: re-aiming per step, the kicker magnet holding balls and barrels, the AI losing the ball in the last ~10 cm and finishing on an estimate, and a photo returned unless the AI confirms success. This directly tells the agent what to verify before kicking.

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 sentences, front-loaded with the action and terminating condition, then prerequisites, then the failure caveat. Each sentence carries information, though the parenthetical about the magnet and the two-clause final sentence are slightly dense.

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?

No output schema exists, and the description covers the operation's key traits: preconditions, in-progress behaviour, physical outcome, and a conditional photo return the agent must inspect. For a destructive, no-required-parameter movement tool this is complete enough to call 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 description coverage is 50% (label and max_distance_mm documented, target enum and speed_percent not). The description reinforces the target/label choice ("Give a target kind or the label of an object or taught colour") but says nothing about speed_percent or the distance cap, so it only partially compensates for the gap.

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 ("Drive up to an object the onboard AI can see") plus the terminal condition (until it's in the kicker). The mention of "re-aiming before every short step" and the magnet behaviour separates it from siblings like go_to, face_object, and fetch_ball without needing to open any schema.

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?

Explicitly routes the agent to alternatives when the precondition fails: "If it isn't in view, use face_object or scan_surroundings first." However, it does not distinguish approach_object from neighbouring movement tools such as go_to or explore_arena, so it is clear context without full when-not coverage.

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