Run a WWW audit on one or more URLs

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

Annotations only mark this as a non-read-only, open-world, non-idempotent, non-destructive call; the description layers on the whole async lifecycle (returns `pending`, later `success`/`partial`/`error`), timing expectations, and the consumption model of one URL-quota unit per audited URL. That quota-per-call behavior also explains why idempotentHint=false matters, which annotations alone would not 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-loads what is audited, then lifecycle, then cost and billing — a sensible priority order for an agent deciding to call. Every sentence carries operational content; the 'instant dispatch vs. under a minute to finish' contrast is what motivates the pending-then-poll pattern, so it earns its place rather than being 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?

An output schema exists, so return values need not be spelled out, yet the description still covers the only thing an agent must know about the response: it starts pending and must be re-read with get_audit. Combined with quota, error code, and billing routing, nothing needed for a correct first call is missing.

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 100%, so both parameters are already documented in structured form, and the description's notes on projectId billing and URL protocol largely restate that. The one genuinely additive parameter fact is that each audited URL consumes one quota unit, which shapes how callers size the urls array, but it is framed as billing rather than parameter guidance. Baseline 3 applies.

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 ('audits the given URLs') with explicit scope ('one or more URLs') and enumerates the checked signals: schema markup, breadcrumbs, heading structure, crawlability, authority signals, reading level, writing style. It is cleanly separable from the sibling get_audit, which the description identifies as the read-side counterpart.

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 explicit preconditions ('Check get_audit_usage first'), the read-back path ('read it with get_audit'), and the billing routing decision (supply projectId or omit it). It even names the failure mode a caller will hit when it violates the guideline: `402 plan_limit_exceeded`.

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