diff_doc_health_radar

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

The description declares it a 'Pure function' (no side effects) and details the return values: per-axis deltas, composite delta, grade change, regression/improvement lists with threshold, and one-line verdict. With no annotations, the description carries the burden well.

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 a single sentence that efficiently conveys purpose, usage, inputs, and outputs without any redundant or superfluous 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?

Given no output schema, the description adequately explains the return values. It covers the main behavioral aspects, though it does not specify error handling or validation of inputs, which is acceptable for a pure function with well-defined inputs.

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 describes parameters as objects, but the description adds critical context that they should be the `radar` sub-field from doc_health_radar responses. Despite 100% schema coverage, this guidance significantly improves mapping.

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 clearly states it diffs two doc_health_radar payloads, specifying the exact sub-field to use and listing detailed outputs. It distinguishes itself from sibling tools like get_section_diff by focusing on health radar payloads.

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 guides when to use: when comparing two radar payloads (e.g., yesterday vs today). It also clarifies what to pass (the `radar` sub-field). However, it does not explicitly mention when not to use or list alternatives, though this is implied by the specific context.

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