queen_audit_list

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

Annotations already declare read-only/idempotent/non-destructive, yet the description adds substantial context they do not cover: default 20 / max 100, 30-day retention with a 20,000 id-range backstop, the crash-consistency caveat about an unrecorded terminal send, and per-caller visibility scoping. This is exactly the behavioral context annotations cannot express.

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?

Six front-loaded sentences: purpose first, then refusal-row contents, visibility, limits, retention, and a caveat. Dense but each sentence carries non-obvious information; only the ordering/refusal details feel slightly compressed.

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?

With no output schema, the description partially covers return shape ('refusal rows include outcome=refused and the problem', 'newest first') but not the full row structure. For a 2-parameter read tool the retention, scoping, and crash caveats make it largely 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?

At 50% schema coverage only project_id is documented in-schema. The description compensates by explaining limit's default (20) and cap (100) and by restating the visibility rule that governs project_id ('queen may read all targets; other callers see only their own project'), adding meaning beyond the schema.

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 (list) and a precisely scoped resource (confirmed queen writes and refused cross-project guard calls, newest first). No sibling shares this 'audit' surface, so the scope is unambiguous and an agent can tell exactly what it returns.

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 content and visibility rules imply an auditing/inspection use case, but there is no explicit when-to-use statement, no prerequisites, and no named alternative. Usage is left to inference rather than stated.

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