Scan multiple live webpages for SEO issues

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, which fully cover the safety and side-effect profile. The description adds the 'independently' qualifier (scan is autonomous, not dependent on prior actions) and clarifies return format (affected URLs with issue codes and evidence). It does not describe potential rate limits or failure behavior for inaccessible pages.

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?

A single, compact sentence with zero wasted words. It captures the action, the scope limit, the input requirement (public, live), and the output format in one breath. The title also reinforces the purpose. This is appropriately front-loaded and efficient.

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?

Given the tool has only one parameter, full schema coverage, and comprehensive annotations (read-only, idempotent, non-destructive), the description is adequate. It specifies the return format (URLs with issue codes and evidence), which is useful despite the lack of an output schema. The main gap is the lack of differentiation from the singular seo_scan_page sibling, but for a bulk-scan tool with these annotations, the description covers the essentials.

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%, with a single 'urls' parameter already described as 'One to 20 public webpage URLs'. The description adds that URLs must be public and live ('live webpages' in title, 'public webpages' in body), which provides slight marginal value beyond the schema. However, it doesn't specify URL format requirements or whether mixed valid/invalid URLs are tolerated.

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 clearly states it scans webpages for SEO issues and returns affected URLs with issue codes and evidence. The verb 'scan' plus resource 'webpages' is specific. However, it doesn't distinguish itself from the sibling tool 'seo_scan_page' (singular), and the distinction between single-page and multi-page scanning is only implied through the max 20 limit in the schema, not explicit in the description.

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?

The description notes it scans 'public' webpages and imposes an upper bound of 20 pages. However, it does not explain when to use this multi-page tool versus the singular 'seo_scan_page' or 'seo_recheck_page' siblings. No exclusions or relative guidance (e.g., use this for bulk checks, use singular for a single URL) is provided, so the agent must infer the appropriate usage context.

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