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

Annotations already declare readOnly, idempotent, non-destructive behavior, so the safety profile costs the description nothing. In exchange the description discloses the return payload with no output schema present — the complementary saturation point plus density, enthalpy, entropy, viscosity, thermal conductivity and surface tension on both liquid and vapor sides — which is exactly the kind of context the annotation block cannot carry.

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 core capability and the EITHER/OR choice are front-loaded in the first clause, and the trailing 'Do not pass both' sentence is a short, high-value constraint. The main sentence is dense, but every clause carries information; only the output enumeration could be tightened.

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?

With no output schema and no nested objects, the description does the needed work by enumerating returned properties and stating the one-parameter-of-two rule. Minor gaps remain — nothing about behavior at or above the critical point, where no saturation boundary exists.

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 coverage is 100%, and the enum units and 'omit if passing the other' notes are already in the schema, so the description can only reinforce rather than add. The mutual-exclusion emphasis and the ~76-fluid scope are mildly useful framing, but no unit-default or fluid-naming detail is added beyond structured fields.

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?

It states a specific verb-resource pair — 'liquid/vapor saturation (phase-boundary) properties' for NIST reference fluids — and the parenthetical plus the enumerable outputs make the scope unambiguous. An agent can distinguish it from the general nist_fluid_properties and nist_fluid_list siblings 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?

It gives an explicit either/or rule ('give EITHER a saturation temperature ... OR a saturation pressure') and a hard exclusion ('Do not pass both temperature and pressure'), plus a concrete use case (boiling point at 1 atm). It does not, however, name the sibling tools an agent should prefer for non-saturation queries, so routing guidance stops short of 5.

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