diagnose_bunkerweb

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

The readOnlyHint annotation is consistent with 'Read-only report'. Beyond that, the description discloses a non-obvious behavioral trait: failed checks surface as FAIL or null rather than raising an error, which prevents an agent from misinterpreting a missing value as a tool failure.

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 sentences, no filler: the scope and per-service extension come first, and the alternative-tool pointer comes last. Every clause carries information an agent needs.

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 compensates by enumerating the report's contents (reachability, auth, version, MULTISITE/instance counts, and per-service existence/draft/owners) and by explaining how failures are represented. That is sufficient for a single-optional-parameter diagnostic tool.

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 the schema already explains that `service` is an optional service ID (its first SERVER_NAME) that checks existence, draft state and setting owners. The description restates this almost verbatim, adding little new meaning; baseline 3 applies.

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 ('Read-only report on the connected BunkerWeb') and enumerates exactly what it covers: API reachability, authentication, version, MULTISITE and instance counts, plus the extra scope when a service ID is supplied. It is clearly distinguishable from the sibling diagnostic `ping_api`.

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?

Explicitly routes the agent to `ping_api` when only a bare probe is needed, which establishes when not to use this tool. It does not spell out prerequisites (e.g. that an instance must be connected) or other alternatives like `search_bunkerweb_docs`, so it falls just short of fully explicit guidance.

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