check

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

With no annotations, the description does real work: it declares the operation read-only, lists exactly what is validated, and discloses the important non-obvious coupling that writes execute this check and abort on new problems. What it does not disclose is how results are surfaced (report vs. error) or whether severity/ordering matters.

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?

Two dense sentences that lead with the operation and its read-only nature, then the rollback coupling. The long enumeration is information-bearing rather than padding, though it could be split for readability.

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 simple single-parameter, read-only tool this covers intent and scope well, but with no output schema the description should explain what a check returns (list of problems? a pass/fail?) and how problem categories are reported. That missing piece leaves an agent unable to interpret the result.

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 0% for the single 'domain' parameter, and the description never clarifies what a domain identifier looks like (name, slug, path). The repeated use of 'domain' implies it is a container with an index and summary, but gives no usable detail for supplying the value.

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 ('Read-only check') and resource ('a domain') and then enumerates the concrete problems it detects (broken links/anchors, missing index notes, missing domain summary, duplicate paragraph claims, decision records without exactly one Status line, stale live sources). No other sibling (move, brief, search, read, links, patch_*) performs validation, so it is distinguishable, though it never explicitly says so.

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 implies usage by noting the same check runs inside every write and rolls the write back, which hints that calling it directly is a pre-flight/diagnostic action rather than a mandatory step. It gives no explicit when-to-use or when-not-to-use statement and names no alternative tool.

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