doctor

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

With no annotations provided, the description carries the full burden and does well: it states 'Changes nothing' and then explicitly discloses the one side effect — the access probe opens and deletes an empty edit — which is exactly the non-obvious behavior an agent needs before calling a diagnostic against a live account. It does not describe the shape of the report returned, which is a remaining gap given there is no output schema.

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 the purpose, then a dense but purposeful checklist and a clear side-effect caveat followed by the usage trigger. Every clause maps to a distinct behavior; the enumeration is long but each item earns its place, with no filler.

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?

Covers what is checked, the sole mutation side effect, and when to run it — sufficient for a shallow, zero-required-param diagnostic. The notable omission is any indication of what the diagnostic report contains (pass/fail per check?), which matters more here because no output schema exists to fill that in.

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?

Only one optional parameter with 100% schema coverage, so the schema already gives type and an example. The description adds real meaning by tying packageName to its effect: it enables the check of whether the service account can actually reach a given app, telling the agent why it would supply it rather than just what it is.

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?

Specific verb (Diagnose) plus the resource (the setup), followed by an enumerated list of exactly what is checked: Node version, credential presence/parseability, token issuance, app reachability, Reporting API, safe-mode settings. This is clearly distinguishable from every sibling, which are all Play/Reporting domain operations rather than environment diagnostics.

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?

Explicit trigger given: 'Run this first if something isn't working,' which tells the agent the entry point for failure triage. It stops short of stating when-not to use it or naming alternatives (e.g. calling get_app_details when only app metadata is needed), so it is strong but not a full routing rule set.

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