run_project_audit

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

Adds rich context beyond the annotations: it discloses that immutable reports are persisted, that old snapshots are pruned to project retention (explaining the destructiveHint), the ten-minute timeout, the single-run-per-project limit, and that alerts remain local with no email/messaging/webhook. This is exactly the behavioral detail the annotations cannot convey.

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 verb and its outputs, followed by constraints and a clear hand-off pointer. Every sentence carries information; it is dense but not padded.

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 the destructive/non-idempotent profile, persistence, retention pruning, timeout, and return pointer well enough for a non-idempotent mutation tool with no output schema. It stops short of saying what happens on a second run for the same project (error vs queued), a notable gap given non-idempotency.

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 coverage is 0%, but there is a single required parameter (project_id) whose meaning is self-evident and reinforced by 'One run per project'. The description adds no extra syntax beyond the schema, but little is needed for a single obvious identifier.

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?

Specific verb+resource ('Fetch a project now, save its immutable report, record verified finding changes') that tells the agent exactly what the tool produces. It partially routes away from get_project_audit, though it does not distinguish itself from near-name siblings like site_audit or audit_live_site.

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?

Explicitly states the operating constraint ('One run per project; ten-minute timeout') and names the follow-up alternative with its condition ('use get_project_audit for the full snapshot'). Lacks explicit when-not-to-use guidance relative to the other audit siblings, but the routing to get_project_audit is clear.

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