diagnostic_summary

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

With no annotations provided, the description carries the full transparency burden and succeeds. It discloses that the tool is side-effect-free ('changes nothing'), available despite misconfiguration ('ungated on purpose'), scoped to the caller's own config ('never fleet rows or vault secrets'), and it describes the conditional behavior around fleet severance assertions. It also states the output includes a verdict with named problems and fixes.

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 description is long but dense and well-structured: it front-loads the core diagnostic question, then lists the report contents, then adds safety/usage caveats, and closes with the fleet-severance behavior. Every sentence adds distinct operational information, and the complexity of the tool justifies the length. There is no filler or repetition.

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?

Despite having no output schema or annotations, the description is remarkably complete. It covers what the tool checks, the verdict format, named problems/fixes, privacy boundaries, behavior under misconfiguration, side-effect-free execution, and conditional env-var-driven fleet severance reporting. An agent has enough information to decide when to invoke it and what to expect from 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?

The schema has one optional app_id parameter with a default and 0% schema description coverage. The description mentions 'your app_id's manifest + resolved permissions,' which hints that app_id selects whose configuration is reported, adding some meaning beyond the bare schema. However, it never explains how the default empty string behaves, what values are valid, or how this parameter relates to the current process identity, leaving a notable gap given the low schema coverage.

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 opens with 'Self-check: is this willow-mcp install wired correctly?' and then enumerates a precise list of checked components (SOIL store, Postgres, schema mapping, manifest/permissions, identity bindings, task worker, egress lease, fleet severance, environment) followed by a verdict. This clearly identifies both the verb (self-check) and the resource (the full willow-mcp install), distinguishing it from sibling read-only tools like env_check, store_stats, and fleet_status by its comprehensive diagnostic scope.

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?

The description gives clear usage context: this is an ungated self-check that must work even when the manifest or database is misconfigured, and it explicitly states it 'changes nothing.' It also explains when fleet-severance checks activate based on environment variables. However, it does not explicitly name sibling alternatives or provide a 'use this instead of X when...' guideline, so it stops short of a 5.

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