list_evaluations

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

With no annotations, the description carries the burden and does so reasonably: it discloses page-numbered pagination, a page_size cap of 100, and that attack-technique/goal detail is nested in each item's config. It doesn't mention auth requirements or the shape of returned items, keeping it from a 5.

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?

Front-loaded with the core purpose, then filters, then behavioral notes, then a sibling pointer. Sentences are dense and largely earn their place, with only minor redundancy around the adversarial-probe detail.

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?

There is no output schema and no annotations, so the description is the only guide. It covers purpose, two filters, and pagination limits, but leaves the 'order' parameter undocumented and doesn't hint at returned fields, leaving the agent partially equipped.

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 0%, so the description must compensate. It documents 'search' (substring match on name), 'approach' (values 'probe'/'metric'), and the page_size cap, but leaves 'page' and 'order' entirely unexplained — a meaningful gap given five params.

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 opens with a specific verb+resource: 'List evaluation definitions (probes/metrics), including red-teaming adversarial probes.' It clearly conveys scope, and the closing pointer to get_evaluation signals the relationship to a sibling tool, though the differentiation is more about depth than a hard routing rule.

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?

It names the available filters and their semantics, and explicitly says to 'Use get_evaluation for full config detail,' giving an alternative for the deeper-lookup case. It lacks explicit when-not-to-use guidance, so it falls short of a 5.

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