start_audit

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so safety is partly covered. The description adds genuinely useful behavior: the job is durable, it returns a job ID, new crawls use a provisional preset, and progress requires audit_status checkpoints. It omits auth/permission requirements and what happens on failure.

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 tight sentences, front-loaded with the core action and input rule, followed by config options and the return/next-step note. Every sentence carries information, with only minor density in the config clause.

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 write tool whose annotations cover the safety profile, the description covers inputs, default behavior, return value (job ID) and the follow-up workflow despite no output schema. The main gap is the two undocumented optional params (siteName, clientName) given 0% schema coverage.

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 carry the load. It conveys meaning for crawlId, url, configPath ('absolute native') and useCurrentConfig ('explicitly'), and the 'exactly one' constraint is real value. However, siteName and clientName are entirely 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 and resource ('Create a durable audit job') plus the exact input constraint ('from exactly one native database crawl ID or a new site URL'). This clearly distinguishes start_audit from siblings like audit_status and control_audit 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?

Gives concrete selection context: use a crawl ID for an existing crawl or a URL for a new one, new crawls default to the technical-audit-v1 preset, and audit_status advances the job. It routes the agent to a sibling for the next step, though it never states a when-not-to-use condition.

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