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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the bar is lower, yet the description still adds real behavior: bounded and stably ordered paging, independent source/target ownership checks, and the warning that 'a stored target is not live publication proof'. It does not state what happens when crawl_id is stale or missing, but the substantive caveats go well beyond the annotations.

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?

Three tight sentences, front-loaded with the core action and payload before the scope disclaimers. The vocabulary is dense (version/validity/ownership phrasing) but no sentence is redundant; only the repeated read-only disclaimers push slightly against conciseness.

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 no explanation, and the description still flags the version fields an agent needs for a later insertion. For a paginated, versioned read the definition is nearly complete; the only omission is any note on what an empty page or exhausted cursor looks like.

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 baseline is 3; the description nonetheless adds meaning by framing crawl_id as 'one saved organization crawl' and paging as 'bounded, stably ordered' pages, reinforcing that cursor must come from a preceding page with identical filters. It does not restate the status enum or page_size ceiling, which the schema already documents.

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: reading paginated internal-link suggestions from one saved organization crawl, and enumerates the payload (literal anchor/context, source entry version, target validity). The negative clause 'does not approve, generate, insert or publish links' sharply bounds the operation, though it never names the closest sibling (webanto_get_internal_link_report) to route against.

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 clear usage context: it is a read over already-saved suggestions whose versions 'can prepare a separate reviewed insertion', and it explicitly excludes approving, generating, inserting or publishing. That tells the agent the tool is a pre-insertion inspection step, but no named alternative is offered for the generation or approval paths.

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