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

With no annotations at all, the description carries the full burden and largely meets it: it discloses that no payment/x402 challenge is involved, that calling is direct, and that the material is a pinned public corpus so reports are reproducible from it. That is real behavioral context beyond a bare 'returns criteria' claim. What is missing is any hint about response shape or size (e.g., whether the doc is returned whole or paged), which matters for a spec too large to summarize.

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 content inventory is front-loaded, which is good, but the following clauses are appended with bare dashes as a run-on ('... reproducible from them. - no payment required ...'). The 'before paying' framing and the 'no payment required' note momentarily read as if they conflict before the parenthetical resolves it, costing a pass of re-reading.

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 zero-param documentation fetch with no annotations and no output schema, the description supplies the essentials: what the payload contains, what it costs (nothing), and an HTTP equivalent path. An agent knows it can call this immediately and that the result is a self-contained spec. Only the delivery format (JSON envelope vs raw text) is left unstated.

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?

The input schema is an empty object and the context confirms zero parameters, so there is nothing for the description to disambiguate; the baseline for a no-parameter tool applies. The description correctly implies no inputs are needed by framing the call as direct and free.

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 the resource precisely ('the published criteria for the Scope Hygiene service (memory-scope-hygiene/v1)') and enumerates its contents: input contract and caps, five factor rules, sharing-marker convention, extension rule, assessability matrix, test corpus identity. That is far more specific than a bare criteria-fetch label. It stops short of naming the siblings scope_hygiene_audit / scope_hygiene_precheck, so the distinction is inferred from the word 'criteria' rather than stated.

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?

'Read these before paying - every report is reproducible from them' establishes a clear use condition: consult the spec ahead of consuming the paid audit/report. The free-call note reinforces that this tool is the cheap prerequisite step. No siblings are named explicitly and no exclusion is stated, so it is clear context rather than a full when/when-not routing rule.

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