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

The description asserts "Read only," while the annotation declares readOnlyHint=false, a direct conflict in the safety signal an agent relies on. The remaining context (practice mode, separate refusal log, credential requirement) is useful, but the contradiction undermines the behavioral claim.

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?

Three short, front-loaded sentences with no filler: mode, action, scope, prerequisite. Every clause carries information.

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 single-parameter, no-output-schema read tool, the description covers origin of the data (separate refusal log), the caller's own scope, and the auth prerequisite. Return shape and pagination are absent but no output schema exists to define them, leaving a minor gap.

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% and the single actor_token parameter is fully documented in-schema (including where to obtain it), so the schema carries the semantics. The description only restates that the token is required, adding no format or scope detail beyond it.

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 ("list your own refused calls") and pins the scope to the caller's own actor plus the dedicated refusal log, which separates it from the institutional/audit siblings. It does not explicitly name a sibling alternative, but the scope qualifiers make the target unambiguous.

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?

"Practice mode" and "Requires your actor_token" give implied context and a prerequisite, but there is no explicit when-to-use/when-not or pointer to an alternative way to inspect refusals. Usage is inferable rather than stated.

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