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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral fact beyond that: low or unknown agreement blocks automatic promotion. It does not describe the shape of the returned status values or what 'flag-only' means operationally, so the added context is real but thin.

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 description is dense and front-loaded: purpose first, then usage, then next step, then limits, then example. Every clause carries information, though the 'Next step' instruction reads as workflow guidance rather than tool documentation and slightly dilutes the focus.

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 must convey what is returned, and 'judge approval, version, and human agreement' does that at a high level. Combined with the promotion-blocking limit and the flag-only caveat, an agent has enough to call it and interpret the result, though the meaning of templateId remains unexplained.

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?

There is a single required parameter, templateId, with 0% schema description coverage, so the schema explains nothing about it. The description only supplies an example object ({"templateId":"uuid"}), which merely restates the uuid format already in the schema and never says what the template identifies. It does not compensate for the coverage 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?

The description opens with a specific verb and resource: 'Read judge approval, version, and human agreement,' which tells an agent exactly what data comes back. It is distinguishable from judge_propose and llm_judge_get, though it never names those siblings explicitly, so the differentiation is only partial.

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?

It gives an explicit positive trigger ('Use when a trial needs a judge') and an explicit exclusion ('Do not use when you need to approve a judge'), which routes the agent away from the approval path. It also prescribes a follow-up ('tell the user if the judge is flag-only; otherwise check experiment_status'), but it does not name the concrete alternative tool to call for approval.

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