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

The annotations already declare readOnlyHint=false and destructiveHint=false, so safety is partly covered. The description usefully adds that results are persisted as annotations, which explains what the write actually touches. It says nothing about the LLM call itself, however: latency, cost, whether it blocks, or what happens if the execution has no suitable output.

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?

A single sentence with no filler, front-loaded with the action and ending on the persistence side effect. Nothing is repeated from the title or 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?

With no output schema, the description should convey what an agent gets back or must do next, and it only hints via 'persist its annotations'. For a tool that triggers an LLM evaluation, the absence of any note on runtime behavior or retrieval of results leaves a real gap.

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%, with each of the three UUID parameters described in the schema. The description adds no meaning beyond that, notably omitting what stepId scoping does to the evaluation. Baseline 3 is appropriate when the schema carries the parameter burden.

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 names a specific verb (Run), a specific resource (an LLM-as-a-judge template) and a specific target (a tenant workflow execution), plus the side effect of persisting annotations. That is enough to separate it from llm_judge_create/update/list/get. It never explicitly contrasts itself with workflow_judge_set or judge_propose, so it stops short of a 5.

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?

Usage is only implied: the required templateId and executionId make clear this is a post-execution evaluation step. There is no explicit statement of when to prefer this over workflow_judge_set/get or judge_propose, and no stated prerequisites such as the execution having finished or the template existing.

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