request_audit

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

Beyond the annotations (which only say non-read-only, non-idempotent, open-world), it discloses the asynchronous dispatch mechanism, that a background worker launches the orchestrator, that the caller performs no repo checkout, and the exact per-project outcome statuses including 'unknown_project'. This is materially useful behavioral context for a fire-and-forget dispatch tool.

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?

Front-loaded with the action, then parameter semantics, then mechanism, then return shape — a logical order with no filler sentences. It runs a bit long in one block and the parenthetical about SSH/watch commands could be trimmed, but every sentence 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?

With no output schema, the description does the right thing by spelling out the per-project result shape ('queued' with dispatch id and attach_command, or 'unknown_project'). Gaps remain: `as_agent` is undocumented and the text says 'one or more projects' while the schema marks no parameters as required, leaving an ambiguity an agent must guess at.

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%, and the description compensates for only one of two parameters, clarifying that `projects` is a list of project slugs or ids (the bare schema gives an untyped array). The `as_agent` parameter is never mentioned anywhere, leaving its meaning and permission implications entirely opaque.

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?

The description names a specific verb and resource ('request a full audit run'), scopes it ('for one or more projects'), and describes the resulting side effect (queued on an audit-dispatch outbox). It is clearly distinguishable from siblings like cancel_audit or list_projects without opening any schema.

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 'Admin:' prefix sets the privilege context and the phrasing 'full audit run' implies the trigger scenario, but the description never states when this should not be used or points to cancel_audit as the inverse operation. Usage is clear, exclusions are absent.

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