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

With no annotations, the description carries the full burden and does a decent job: it discloses the nature of the output (computed values plus a ranked checklist), the advisory-not-actionable posture, and an explicit refusal boundary around safety devices and venting. It does not say what happens with out-of-range or inconsistent readings, nor whether any state persists, which keeps it short of a 5.

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 purpose and output are front-loaded in the first sentence, and the safety/certification caveats, while longer, earn their place for a tool touching refrigerant handling. The trailing 'metering' line reads slightly like an afterthought appended to the paragraph rather than being integrated.

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 7-parameter tool with no annotations and no output schema, the description adequately conveys the diagnostic flow and advisory posture, and the psig/_f parameter names encode units. It is nonetheless incomplete on parameter expectations and edge-case behavior, which matters given six required inputs that determine correctness of the computed diagnosis.

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 0% across 7 parameters, so the description must compensate. It explains only 'metering' ('txv' default, or 'fixed' for fixed-orifice/piston systems), leaving refrigerant, suction_psig, head_psig, and the two line temperatures plus ambient undocumented beyond their self-evident names — no unit expectations, valid refrigerant naming, or expected ranges.

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 names a concrete verb+resource ('conversational diagnostic copilot' that takes field readings and returns computed superheat/subcooling plus a ranked 'check this first' list). This clearly distinguishes it from the sibling primitives superheat, subcooling, pt_lookup and pt_reverse, which return single measurements rather than a ranked diagnosis.

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?

It states the intended audience (certified HVAC technicians, EPA 608 / A2L) and hard limits ('informational only', never how to defeat a safety device), which scopes use appropriately. However it never says when to pick diagnose over superheat/subcooling/pt_lookup, nor what conditions make the copilot the right call — usage is implied by the output description only.

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