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

Annotations already declare this a read-only, idempotent, non-destructive, closed-world call, but the description adds genuinely new behavioral facts: batching up to 10 ids yields smaller neighbor samples and anchor diagnostics 'counted by kind', the missing_site_url_ids return field flags pages with no link metrics, and 'unavailable no_site_crawl' reports a missing crawl. Pagination via next_cursor is also disclosed. This is well beyond what the annotations 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?

The return payload is front-loaded and the routing and batching/pagination rules follow in a logical order. The dense enumeration of returned metrics is long but each clause carries distinct information; a light restructure into separate sentences would improve scanability without cutting content.

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 must carry the return contract, and it does: metric inventory, sampling behavior, missing-id reporting, pagination, and an error code. For a five-parameter read tool with full annotation coverage, an agent has everything needed to call it correctly on the first attempt.

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 meaning the schema cannot: it explains that site_url_ids come from read_site_pages, that batching changes the response shape (smaller samples), and that omitting ids pages through every page. It also describes cursor semantics ('pass next_cursor for more') despite the schema naming the field 'cursor', which is a small naming mismatch rather than a fatal gap.

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 names a specific verb and resource ('Read the internal links of crawled pages') and then enumerates exactly what each row contains: inbound/outbound counts overall and in main content, nofollow inbound, click depth, bounded neighbor samples with anchors, and anchor diagnostics. It also explicitly separates itself from read_site_pages ('for page scores and issues'), so an agent can choose between them without opening either 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?

It gives a concrete motivating use case ('find orphaned or buried pages') and routes to the right alternatives: read_site_pages for page scores and issues, read_site_health as the source of crawl_id. What is missing is an explicit when-not-to-use beyond those sibling pointers, so it falls just short of the full when/when-not/alternatives bar.

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