agent_eval_plan

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile needs no restatement, and the output schema covers return values. The description adds that the plan is derived deterministically from explicit capabilities and risks, but says nothing about determinism of recommendations, depth/verbosity of the plan, or limits on the scenarios it can cover.

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?

A single front-loaded sentence that packs the verb, resource and deliverable list with no filler. Slightly dense in its comma-list form but nothing is wasted.

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 tool with five required parameters, an object array, and an output schema, the description covers the overall intent but leaves the agent guessing what 'agent' and 'tools' should contain and how much detail to supply. Adequate to call, but not complete.

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 description coverage is 0%, so the description must carry parameter meaning, yet it only touches two of five inputs (capabilities, risks) plus an oblique nod to releaseCadence via 'regression cadence'. The 'agent' identifier and especially the 'tools' array with its {name, mutating} shape — a materially important input for red-team and guardrail design — are never explained.

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 ('design') and resource ('evaluation plan for an AI agent') and enumerates the five deliverables (golden set sizing, metrics, judge rubric, red-team cases, regression cadence), so an agent knows exactly what it gets. It does not, however, name or contrast any sibling such as agent_tool_contract or prompt_injection_checklist, which overlap in the agent/red-team space.

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?

'from explicit capabilities and risks' implies the caller must supply capabilities and risks as inputs, which is weak usage guidance. There is no statement of when to prefer this over agent_tool_contract, prompt_injection_checklist, or implementation_plan, and no exclusions or prerequisites.

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