Delimit Agent Check

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

The description discloses side-effect scope ('read-only on the policy store') and names the underlying API call (ai.agent_policy.check_agent_permission), adding value beyond the annotations. Annotations set readOnlyHint=false, but the description clarifies that the policy store itself is not mutated; it could still have other side effects, which is a minor ambiguity.

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?

Well-structured with front-loaded purpose, explicit usage sections, sibling contrast, and side effects. Every sentence earns its place, and the description is concise without sacrificing necessary guidance.

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?

Covers purpose, when to use, when not to use, sibling differentiation, side effects, and the underlying call. With full parameter schema coverage and an output schema present, an agent has essentially everything needed to invoke this tool correctly.

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 100%, with model and action already clearly described in the input schema. The description reinforces the permission-check context but does not add new parameter-level semantics, so the baseline of 3 is appropriate.

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: 'Check if a model is allowed to perform an action under agent policy.' The sibling contrast explicitly distinguishes this from delimit_agent_policy and delimit_gov_evaluate, so an agent can identify the tool's unique role.

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 'When to use' and 'When NOT to use' guidance, naming the exact alternatives (delimit_agent_policy and delimit_gov_evaluate). This fully routes an agent to the appropriate tool with no inference required.

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