list_evaluators

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

With no annotations, the description carries the full burden and does well: it discloses the exact contents of each entry (newest version id, declared Metrics with name/shape/grain/label vocabulary/scale/range/better) and explicitly notes what is NOT returned ('but not the source'). It also explains the object-store side effect — output is auto-stored and returned as a preview with an @obj_123 ID. Missing only pagination/limits and permission requirements.

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?

Purpose is front-loaded, but the middle paragraph is one very long parenthetical-laden sentence about Metric shapes that is hard to parse, and the closing four sentences are generic object-store boilerplate repeated across tools. The content mostly earns its place, but the structure is uneven and boilerplate-heavy.

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 zero-parameter list tool with no output schema and no annotations, the description covers what an agent needs: return contents, the explicit exclusion of source code, the object-store handoff, and the ownership model. Only result-set sizing (pagination, truncation) and error conditions beyond 'an error message' are absent.

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 nothing for the description to disambiguate; the baseline of 4 applies. The description correctly implies a workspace-scoped, unfiltered listing.

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 Evaluators in the workspace') and then defines what an Evaluator actually is — a versioned Python function that judges a Session and reports named Metrics. That definition plus the ownership note ('belong to the workspace, not to a pipeline') lets an agent distinguish this from get_evaluator and list_metric_groups 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?

The workspace-vs-pipeline scoping and the mention that 'a Metric Group picks which ones a scoring run judges with' implicitly tell the agent where this tool fits. However, there is no explicit routing: nothing says to use get_evaluator for a single evaluator's source, or try_evaluator to test one. Usage is inferable but not stated.

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