request_audit

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

With no annotations, the description carries the full burden and does so well: it discloses the async dispatch via the audit-dispatch outbox, that a background worker launches the orchestrator, that no repo checkout happens for the caller, and the possible return statuses. It stops short of stating explicit permission/auth requirements beyond the 'Admin:' label.

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?

Purpose is front-loaded, then followed by the resolution/dispatch mechanics and result shape. It is fairly dense but each sentence adds operational value; nothing is pure filler.

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 no-output-schema tool, the description usefully explains the return shape (per-project 'queued' with dispatch id and attach_command, or 'unknown_project'). The main gap is the unexplained `as_agent` parameter.

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 compensate. It explains `projects` well as a list of project slugs or ids, but never mentions the `as_agent` parameter, leaving one of two parameters undocumented in both schema and description.

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 (request) and resource (a full audit run for one or more projects), and the 'Admin:' prefix flags the privileged scope. It is clearly distinguishable from the sibling cancel_audit, since this initiates rather than cancels.

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 description implies an admin context and that the caller queues work asynchronously, but it never states when to choose this over alternatives or the conditions under which it should be invoked. Usage is inferred rather than stated.

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