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

With no annotations, the description carries the full burden and does well: it discloses a concrete cost (2 credits), states the operation is read-only with nothing persisted, and describes the return shape. It omits operational limits such as how many pages are crawled, behavior on unreachable sites, or whether a feature flag must be enabled.

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?

Roughly two compact clauses that are front-loaded with the action and return fields, then the cost and safety notes. Nearly every phrase earns its place, though "used by the page-navigation feature" reads as a somewhat unmotivated aside without explaining whether the feature must be enabled.

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 2-parameter, no-annotation, no-output-schema tool, the description does useful work by listing returned fields and stating cost/side effects. It still leaves gaps an agent needs: the website_url format and source, and the crawl scope or limits, neither of which is covered by schema or annotations.

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 50%: `id` is documented in the schema (UUID from list_agents) but `website_url` has no schema description. The description only weakly compensates by implying the URL is the site whose pages are listed; it does not say whether it must be the agent's own configured site, a full URL with scheme, or a different domain.

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 gives a specific verb and resource ("List the pages of a website") and enumerates what each page record contains (path, title, description, keywords), so the agent knows exactly what comes back. It also scopes the call to "this agent" and ties it to the page-navigation feature. It does not distinguish itself from close siblings like scan_website_quick or deep_scan_agent, which keeps it below a 5.

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?

Usage is only implied: the read-only note ("nothing saved") hints that a separate persistence step like save_scan_data is needed if results must be kept, and the credit cost hints at cheaper alternatives. But no sibling is named and there is no explicit when-to-use/when-not statement, so the agent must infer the routing decision.

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