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

Annotations only declare this is a non-destructive, non-open-world write; the description adds real operational context beyond that: external evals require a workspace API key with the ci_evals preset that 'can't be minted from here,' and it explains the draft-vs-published execution behavior at run time. These are meaningful prerequisites an agent would otherwise not know.

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 lead sentence front-loads the core purpose and lifecycle position, and the remaining text is information-dense rather than filler. It runs long and a couple of clauses are heavily packed, but given 12 parameters and two targets, nearly every sentence earns its place.

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 steps in to state what to do with the result ('hand back the eval id and tell the user to create a workspace API key'), and it covers the branching setup, prerequisites, and next-step tool. Nothing an agent needs to call this correctly is missing.

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 92%, so the schema does most of the work (baseline 3). The description still adds relational meaning the schema can't express — flowId is only needed for the workbench target, flowRevisionId applies only to the published stage, and the draft/published distinction is spelled out — lifting it above baseline.

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 — it 'binds a dataset + rubric to something under test as a repeatable eval' — and positions itself in the lifecycle as 'THE LAST SETUP STEP before scoring.' It also distinguishes its job from caliper_evals_run, which does the scoring, so an agent can separate it from siblings without opening any schema.

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?

Explicitly describes the two invocation paths (workbench flow via flowId vs target:'external'), when to pick each, when to use flowStage 'draft' vs 'published', and routes to caliper_rubrics_list when a rubric already exists. It even points at the 'Run evals in CI' docs guide for the external path.

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