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

Annotations already mark this read-only, idempotent, non-destructive and closed-world, and the description still adds substantive behavior: what the check pipeline runs (role/module/delegation/integration), what the response contains (timestamp, availability, missingScopes, access.nextAction), and explicit limits on what availability proves ('neither data completeness nor execution authority'). It also clarifies that detail=full expands descriptions/schemas but does not confer host-callability for undisclosed tools — a real behavioral caveat not present in structured fields.

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?

Front-loaded with purpose and alternatives, then parameters, then return/caveat — a sensible order with no filler sentences. It is dense and repeats a couple of schema rules (empty names array, detail default), which keeps it just short of maximally tight.

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 carries the return-value burden and does so — shape, timestamp, availability, missingScopes, access.nextAction. All three optional parameters are explained, the absence-diagnosis pitfall is called out, and the tool's non-operational nature is stated explicitly.

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; the description earns a bump by stating that names and domain intersect and that detail=full adds schemas but not callability. Much of it (names=[] selects none, the detail default rule, domain never expanding access) restates the schema verbatim, so it is additive rather than transformative.

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?

Opens with a specific verb+resource ('Discover capabilities') and immediately scopes the intent: before picking an unfamiliar action, or when diagnosing a denial. It also distinguishes itself from the nearest siblings by naming get_context (workspace/scopes) and the business read tools (records), so an agent can route 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?

Gives explicit when-to-use conditions, named alternatives, and a concrete invocation recipe ('names=["get_policy"], domain="policy", detail="full"'). It also states the negative case — an empty filtered result is not a full diagnosis, so inspect the unfiltered catalog — which is exactly the kind of exclusion guidance that prevents misuse.

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