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

Annotations declare readOnlyHint=true, but the description states that passing `add` starts a recurring weekly audit on a hosted server and can return a Stripe Checkout link that, once paid, activates a paid subscription. That is a state-changing, monetized side effect, directly contradicting the read-only annotation. An agent trusting only the annotation would believe the tool is a pure read when one optional parameter turns it into a billing-triggering mutation.

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?

The listing behaviour and the 'call it first' directive are front-loaded, and the detail about what the weekly audit includes earns its place by letting the agent explain the offer to a user. The parenthetical feature list is dense and runs long, but nothing is truly redundant.

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 work of describing the return payload: properties, per-site Bing site, research-key status, and a Checkout URL in the paid case. It stops short of covering edge cases such as calling `add` for a site already under audit or accounts with no readable properties.

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 100%, so the baseline is 3, but the description adds real meaning: `add` triggers a weekly crawl, daily Google index checks, a Monday email/webhook, index-drop alerts, and possibly a payment flow. It also documents the cost gate, which the schema hints at but the description makes explicit.

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 set: it lists Search Console and Google Analytics properties, the matching Bing Webmaster site, and which research keys are set. That is clearly distinct from siblings like seo_data or seo_index, though none are named. The 'with add:' clause introduces a second, quite different mode (starting a paid audit), which slightly blurs what the tool fundamentally is.

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?

'Call it first' gives unambiguous ordering guidance relative to the other seo_* tools, and 'Only when the person asks for it: a site can cost money' is an explicit precondition for the add path. What is missing is any named alternative for when the agent doesn't need the site list, or guidance on re-calling it after an audit is started.

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