What should the robot do?

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safe, advice-only nature is partly covered; the description reinforces this with 'without moving.' Beyond the annotations, it adds a genuinely useful behavioral caveat: the holding default comes from the onboard AI and often misses a held ball, so the agent should verify with look(). It does not describe latency or cost, but the key operational gotcha is disclosed.

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?

The purpose is front-loaded in the first clause, and the parenthetical enumerations of return content are dense rather than padded. It is a long run-on sentence with nested parentheses that could be split, but nearly every clause conveys substantive information rather than 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 read-only advisory tool with no output schema, the description compensates well by enumerating what the advice contains (distances, roll times, path clearance). The main omission is speed_percent, but combined with annotations the agent has enough to call it correctly and interpret the result.

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?

With 0% schema description coverage, the description must carry all parameter meaning. It documents holding (defaults to onboard AI's view, unreliable for held ball) and teammates_mm (format [[x, y], …] and purpose 'teammates to pass to'), but speed_percent is never explained despite being a tunable input. Two of three parameters are covered, leaving a real gap on the third.

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 opening clause 'Strategy advice without moving: fetch, shoot, pass or dribble, and why' states a specific verb (advise) and resource (strategy decision) and immediately distinguishes it from action siblings like move, shoot_at_goal, and kick by declaring it is advice-only. It also previews the output content (distance to goal, kick roll distance, path clarity), so an agent knows exactly what kind of decision support it returns.

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?

The description gives clear context for invoking it (deciding between fetch/shoot/pass/dribble) and names an alternative tool to pair with: confirm the holding state with look() because the onboard AI often misses a held ball. It does not explicitly state when NOT to use it (e.g., inside a fast match loop vs. pre-planning), so it stops short of full alternative framing.

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