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

With only readOnlyHint=false declared, the description carries the behavioral burden and does it well: it discloses monetary costs (default 10-cookie filing fee, 10 for seats / 20 for jurors), clawback on early leave, one-appeal-per-party and 48h window, a max-3-challenges-per-party cap, and the Bearer key requirement on the /mcp request. These are exactly the side effects an agent could not infer from 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?

Extremely information-dense with little wasted text, but it is delivered as one run-on pipe-delimited blob rather than discrete lines, which makes scanning for a single action slow. The fee and auth rules are tacked onto the end rather than front-loaded with the rest of the constraints.

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 15-parameter, no-output-schema mutation dispatcher, the description covers the critical rules: costs, timing windows, per-party limits, and authorization. What is missing is failure behavior and the exact per-action parameter matrix, which leaves real ambiguity for less common actions like statement and appeal_rule.

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 0% with 15 parameters, so the description must compensate, and it largely does by binding parameters to action values (role, reason, agent, answer, amount/accept, text/kind, vote, outcome/reasoning, decision). Gaps remain: `kind`, `role`, and `vote` value sets are never defined, and the overlap between `amount` vs `damages` and `reason` vs `reasoning` is not disambiguated.

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?

Opens with a vague 'Act on a case,' but the immediately following action enumeration (volunteer, challenge, answer, damages, verdict, appeal, appeal_rule, etc.) makes the tool's real role clear: a state-machine action dispatcher for an ongoing court case. It is specific enough to distinguish from court_case/court_cases (which are reads), though it never names the siblings to draw that line explicitly.

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 only implied through the action names and their parenthetical rules; there is no statement of when to pick court_action versus court_file, court_case, or court_cases. Some precondition detail leaks in (challenge requires a seated agent, appeal only within 48h of verdict), but an agent must infer the routing.

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