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

Annotations already establish readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered by structured data. The description's real addition is disclosing the returned content (questions, version, per-question recent average, human agreement, flag-only state), which matters because there is no output schema, but it says nothing about what happens when no judge exists.

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 with the verb and resource, then the returned fields, the usage rule, and an example—every clause carries information. The field enumeration is dense but justified given the absence of an output schema.

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 single-parameter read tool with no output schema, the description covers purpose, return contents, call format, and a usage cue. The remaining gaps are the empty/no-judge case and explicit disambiguation from llm_judge_get and judge_status.

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% and the single workflowId property is bare (string, minLength 1). The inline example {"workflowId":"invoice-flow"} compensates by showing the expected identifier format, though it doesn't clarify whether a numeric ID would also work.

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 verb 'Read' plus the resource 'the quality judge of one workflow' is specific, and the description enumerates what the judge record contains (questions, version, recent averages, human agreement, flag-only state). It stops short of distinguishing this from adjacent siblings like llm_judge_get or judge_status, which an agent could easily confuse it with.

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?

'Use before you change a judge' gives a concrete triggering condition, implicitly pointing at workflow_judge_set as the follow-up call. It never names that sibling explicitly and offers no exclusion against llm_judge_get, so the when-not guidance is missing.

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