list_evaluator_templates

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

With no annotations provided, the description carries the disclosure burden well: it names the fields returned, flags per-Session model cost for judge_model templates, warns that copies diverge from the template, and mentions error returns. The object-store boilerplate is generic but does explain the auto-stored output and @obj_ ID.

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 core sentences are front-loaded and informative, but the :returns: docstring line and the generic object-store paragraph are boilerplate that repeat framework conventions. The cost warning and copy-does-not-follow caveat earn their place; the trailing block does not.

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 does the work of enumerating returned fields and explaining the object-store preview, so an agent knows what to expect. Cost implications and the create_evaluator handoff complete the picture; only an explicit when-not-to-use note 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?

The tool takes zero parameters, so there is no parameter semantics to add and the baseline of 4 would normally apply. However, the description's field listing (key, name, category, python_code, judge_model, expected_columns) describes return values rather than parameters, so it is helpful context but not parameter guidance; a 3 reflects that neutral fit.

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 ('Lists the built-in Evaluator templates') and clarifies what a template is ('ready-made Evaluation Functions to start from'), which separates it from the user-created evaluator tools like list_evaluators. It does not explicitly name sibling list/search tools, so it stops short of full sibling differentiation.

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?

Gives a clear follow-up path: pass a template's name and python_code to create_evaluator, and warns that the resulting copy does not track the template. It also notes judge_model templates cost money per Session. It lacks an explicit statement of when to prefer this over search_templates or list_evaluators.

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