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

Annotations only declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the description usefully adds lifecycle semantics: the judge remains 'proposed' and has no effect until a person approves it, and a second proposal call is required. It omits anything about permissions, rate limits, or what the proposal response contains, so it is strong but not exhaustive.

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?

Usage rule, exclusion, next step, and limit are front-loaded in short sentences with no filler. The trailing raw JSON example is a bit bulky but does anchor the required top-level shape.

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 mutation tool with a large nested schema and no output schema, the description covers the lifecycle and follow-up well but leaves the config envelope — the part an agent will most likely get wrong — undocumented. No output schema means the description could also say what a successful proposal returns.

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 only 20% across 5 parameters with a deeply nested config (prompt, model, scope, provider, questions with three variants, samplingRate, scoreConfigs), and the description explains none of it. The inline example shows 'config':{} with no guidance, which is misleading given that config requires a prompt field.

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+resource: 'Propose a typed workflow or node judge,' which tells an agent exactly what object is created and that both workflow-level and node-level judges exist. It is distinguishable from siblings such as llm_judge_create or workflow_judge_set, though it never explicitly names those siblings as alternatives.

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 a positive trigger ('Use when an update needs quality checks') and a negative one ('Do not use when you need to approve or change a frozen judge'), plus an explicit next step (metrics_propose + human approval). It stops short of naming the concrete alternative tool for the excluded case, leaving the agent to infer workflow_judge_set or llm_judge_update.

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