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

With no annotations, the description carries full responsibility for transparency. It merely states 'Returns: {input}' without explaining behavior (e.g., handling of invalid units, case sensitivity, precision, or what happens when from and to units are the same). This lack of detail undermines an agent's ability to anticipate results.

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 concise with three short sentences, directly stating the purpose, use cases, and input/output. It is front-loaded with the core functionality. However, the vague return description and the mention of 'list_bundles' could be streamlined.

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?

The description fails to resolve a critical inconsistency: it lists units (MPa, torr) not present in the input schema enum, creating a potential error source. Given the tool's simplicity, the description should align with the schema and clarify case sensitivity. The existence of an output schema mitigates some need for return documentation, but the mismatch significantly reduces completeness.

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% (each parameter has a description), so baseline is 3. The description only repeats parameter names ('value, from-unit, to-unit') and adds no extra meaning beyond what the schema already provides. No parameter-specific guidance is given.

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 the tool converts pressure between specific units (Pa, kPa, MPa, bar, psi, atm, mmHg, mbar, torr). It distinguishes it from sibling convert tools by specifying pressure. However, there's a mismatch: some units mentioned (MPa, torr) are not in the input schema enum, which may confuse an agent.

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?

The description provides basic usage contexts ('engineering, tires, weather') and references 'list_bundles' for related calculators. It does not explicitly state when to use this tool over alternatives or give exclusion criteria, providing only minimal guidance.

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