paper_doctor

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

With no annotations, the description carries the full behavioral burden. It does valuable work by defining the meaning of a successful result ('ok means a render actually succeeded, not just that quarto exists'), which is exactly the kind of context annotations could not provide here. It does not disclose side effects such as where the minimal document is written, whether artifacts are left behind, or how failure is reported.

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?

A single sentence with no filler; the action comes first and the crucial interpretation of the result follows the semicolon. Every clause adds distinct information.

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?

For a zero-parameter diagnostic with no output schema, the description covers the essentials: what is run and how to interpret success. It stops short of describing the failure shape or any filesystem effects, which the agent would still have to discover by calling it.

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 tool takes zero parameters, so the baseline is 4 and there is nothing in the schema that the description needs to compensate for. Nothing in the description conflicts with the empty parameter list.

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 states a specific action: probe the render toolchain by rendering a minimal document. It implicitly distinguishes itself from paper_render by framing the render as a probe rather than a real build, though it never names paper_render as the alternative. The agent can tell what the tool does without opening the 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?

Usage is implied by the diagnostic framing ('probe', 'ok means a render actually succeeded'), suggesting this is a sanity-check tool to run before real renders. However, there is no explicit when-to-use statement, no mention of when to prefer paper_render instead, and no note about when this check should be repeated.

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