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

Adds real context beyond the annotations: edits mint a new version rather than mutating in place, a person must approve it, and the server retains trial-locked versions. That is useful, but for a tool annotated destructiveHint=true it says nothing about what is lost or whether the previous version is preserved or invalidated.

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-loaded and clearly segmented with 'Use when', 'Do not use', 'Next step', 'Limits' and a concrete example; every line carries signal. The telegraphic style borders on clipped and the example illustrates almost nothing given the schema size.

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 destructive mutation over a large nested payload with no output schema, the definition covers the workflow and approval path but not how to shape the config, how partial edits behave, or what a version change returns. The heaviest part of the call, the config object, is entirely unaddressed.

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 description coverage is 14% across 7 top-level parameters and a deeply nested config object with prompt, model, provider, questions, scoreConfigs and samplingRate. The description only shows templateId and name in a single example, leaving the entire config surface undocumented in both schema and prose.

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 and resource ('Edit a proposed judge or propose a new version'), which distinguishes it from in-place mutation. It does not name the sibling tools (llm_judge_create, judge_propose, workflow_judge_set) it differs from, so the agent must still infer which creation path to take.

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?

Gives an explicit trigger ('Use when a person requests a judge change') and an explicit exclusion ('Do not use when you need to change an approved or frozen version in place'). It also supplies the follow-up sequence via judge_status plus human approval, though it never names the tool to use instead for frozen versions.

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