list_eval_criteria

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

Discloses that Free plan can read all criteria but creating custom ones is Pro+, and existing rows remain visible after downgrade. No annotations exist, so description fully carries the burden. For a read-only listing tool with no parameters, this is highly transparent.

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?

Three sentences, no fluff. Front-loaded with main purpose, then details and usage guidance. Every sentence adds value.

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?

Given no parameters and no output schema, the description is complete: explains output fields, global vs custom, plan limitations, and usage context. Nothing missing for this simple listing tool.

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% but there are no parameters. The description adds meaning by detailing the output fields (id, name, rubric, scaleMin, scaleMax) and the distinction between global and custom criteria. This compensates for the lack of parameters.

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 clearly states it returns the list of LLM-as-judge evaluation criteria, including 5 global defaults and custom criteria, with specific fields (id, name, rubric, scaleMin, scaleMax). This distinguishes it from sibling tools like create_eval_criterion, get_eval_criterion, and others.

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?

Provides explicit usage guidance: 'Use before running an eval to see which axes are available.' Also notes plan limitations (Free vs Pro+), helping set expectations. No explicit exclusion of alternative tools, but context is clear.

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