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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds that the computation is backed by CoolProp, but says nothing about failure modes for under-specified or over-specified states, output format, or how requested properties that aren't independent are handled.

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?

Compact and front-loaded, but the shorthand is dense and partly garbled – 'g' is never expanded, 'k conductivity' and 'a speed of sound' mix noun labels with definitions, and 'properties' appears both as a listed output and as a parenthetical group. It is short but requires re-reading.

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 5-parameter tool with no output schema, the description should say what comes back and in what form; it lists candidate quantities but not the response shape or error behavior. What it does cover – the state string syntax and the property code glossary – is the most important part.

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 schema leaves the required 'state' parameter entirely undescribed (60% coverage overall), and the description compensates with two concrete spec examples ('T = 25 °C, P = 1 bar', 'P = 1 MPa, sat vapor') that reveal the free-string syntax. It also glosses the property codes (D density, mu viscosity, a speed of sound), which adds real meaning beyond the bare enum.

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?

Names the concrete resource (a fluid's thermodynamic state via CoolProp) and enumerates the computable properties (T, P, h, s, x, v, D, u, cp, cv, mu, k, Pr, Z, a, g). It also distinguishes itself from the sibling by stating 'Processes and cycles: solve_worksheet', so the agent can tell a single-state property lookup from a process/cycle solver.

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 routes the alternative case: processes and cycles belong to solve_worksheet, leaving this tool for single-state property evaluation. No explicit when-not guidance beyond that (e.g., saturation tables vs. single-phase, invalid state handling), but the context for choosing it is clear.

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