Get case

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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar is lower. The description adds value beyond them: the snapshot semantics (each call returns fresh data) and the conditional shareUrl disclosure for private cases you own, including the link-rotation security note. It doesn't state not-found error behavior, but for a read tool with idempotentHint that gap is minor.

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 core purpose is front-loaded ('Fetch one case by id'), and each subsequent sentence earns its place: field enumeration compensates for the missing output schema, the shareUrl note is critical context, and the sibling routing prevents wrong tool selection. Slightly dense with the long field list, but nothing is redundant.

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 correctly compensates by enumerating the return payload (title, description, state, sides with uuid, totalVotes, votePercentage, endsAt/timeLeft, conditional shareUrl). Usage guidance disambiguates the many siblings. The only omission is error handling for nonexistent or unauthorized cases, which is acceptable given the annotations cover the safety profile.

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% — the id parameter is fully described in the schema ('uuid field ... not its numeric id'), including where to obtain it. The description doesn't add parameter format or sourcing details beyond this. Baseline 3 applies since the schema does the heavy lifting.

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 ('Fetch') + resource ('one case by id') and enumerates the exact fields returned, so an agent knows precisely what it gets. It also carves itself out from the await_* siblings by framing itself as the one-shot read versus their blocking behavior.

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 says when to use this tool ('one-shot read', 'call it again for a fresh snapshot') and names the two alternatives with their selection conditions ('block until something changes instead' → tribeunal_await_case_activity for any event, tribeunal_await_verdict for the final decision). Even cross-references tribeunal_cast_vote for the follow-up action. Nothing is left to inference.

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