buzz_doctor

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

With no annotations, the description fully carries behavioral disclosure. It explicitly states 'Read-only; no writes,' explains that it opens a brand-new node:https socket rather than using the shim's normal transport, and discloses that write-health is honestly reported as unverified when no real writes have occurred. It also advertises its limitation as connector-side only.

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 information-dense, front-loading the core purpose and the key constraint before enumerating diagnostic verdicts. Minor redundancy exists ('Read-only; no writes' is stated twice in different forms), but each verdict and caveat serves a real decision-making purpose.

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?

Given there is no output schema, the description goes beyond the minimum by explaining not only what is returned but what each outcome means and how the agent should act on it. It covers identity, pin status, relay dial URL, write-health unverifiability, and timeout defaults, making the tool safely callable without additional external knowledge.

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%: the only parameter, timeout_s, is already described as 'per-probe timeout in seconds (default 5, max 30)' in the schema. The description only restates 'Optional timeout_s (default 5),' adding no meaningful new semantic detail beyond the structured field.

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 a specific diagnostic verb and resource: 'Diagnose why Buzz reads/posts are failing.' It clearly differentiates from all sibling read/write/status tools by emphasizing it is read-only and probes outside the normal wedged transport.

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 implies the right usage context: use when reads/posts are failing and normal transport may be wedged. It also gives a clear exclusion by noting this is 'not the authoritative relay health signal,' which helps an agent avoid over-relying on it. It does not explicitly name an alternative tool, but no sibling appears to be a diagnostic alternative.

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