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

Annotations already declare readOnly/idempotent/closed-world, but the description adds genuinely non-derivable behavior: no new computation, free of credit charges, no external call, and a `notDerivable` block explaining what the report can never compute. The one ding is that it instructs the agent to narrow on `state`, which is not present in the input schema, leaving it unclear whether state is an input filter or a returned field.

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?

Content is front-loaded: what the report contains comes first, then scope disclaimers, then state semantics. It is dense and slightly repetitive ("INTERNAL LINKS ONLY" followed by a full external-links explanation), but nearly every sentence carries distinct scope or data-limitation information.

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 meaningful work describing return shape (totals.externalLinkOccurrences, notDerivable, state values) and the absence-of-data semantics, which is exactly what an agent needs to interpret results. The unresolved ambiguity about whether `state` is an input or an output field is the only real gap.

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% and both parameters (auditId, projectId) are already fully documented in the schema, including the "omitted means latest completed audit" default. The description adds no per-parameter syntax or format detail beyond that, so the baseline 3 applies; its `state` reference matches no declared parameter.

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 report and enumerates its exact contents: outbound/inbound internal link counts per page, orphan pages, dead ends, and click-depth distribution, scoped to a project's latest (or named) completed crawl. It also explicitly carves itself off from external-link tooling, so an agent can distinguish it from siblings like get_backlinks_overview or get_audit_structured_data without opening a 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 strong usage rule ("ALWAYS narrow on `state` first") and explains each state value so the agent knows when an empty result means no crawl vs. missing data. It does not name a sibling alternative for the adjacent use cases (e.g. external links, comparison audits), so it stops short of full alternative routing.

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