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

With readOnlyHint=false and idempotentHint=false declared, the description still contributes real behavior: operations are capped by a CPU budget and max_ticks, the call returns a final score plus a replay receipt, and results are bounded by outside player moves. It never says what the non-read-only write actually records (budget consumption or a stored simulation), which is the remaining gap.

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-loading is good and the text is short, but the trailing example merely echoes the required parameters already listed earlier, and the phrase 'Policy is no stronger than outside player moves' is cryptic enough to cost a read. Nothing is bloated, but not every sentence earns its place.

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?

Output schema exists so return-shape explanation is bonus rather than required, and the 100%-covered schema means parameter detail is not on the description. For a five-parameter, non-read-only tool, the only missing piece is how this differs procedurally from arena_act and whether repeated calls burn budget.

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 coverage is 100% and the enum values are already documented in the schema, so the description's restatement of policy options and the max_ticks cap adds little. The one genuinely additive line, 'Policy is no stronger than outside player moves', clarifies how the policy enum relates to competitive outcomes, but key and guest_token are untouched.

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 states a concrete action ('server-side policy simulation for an active match') with the exact input triple (match_id, policy, max_ticks), which is far more specific than the bare name 'Simulate policy'. It doesn't, however, name a sibling such as arena_act, so the agent has to infer that this simulates rather than submits competitive moves.

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?

A 'WHEN:' clause is present, but it mostly restates scope ('for an active match') rather than giving real decision guidance. There is no explicit when-not, no prerequisite (e.g. must have joined a match), and no named alternative for submitting actual moves.

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