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

With no annotations, the description fully carries the burden, and it does well: it discloses that inputs are validated against min/max and impossible values are refused by name, and that derivation.confidence grades the output with 'none' for incomplete computation. It also notes the citation URL should be shared, which is a behavioral expectation. It does not explicitly state read-only nature, but for a calculation tool that is implied and no contradiction exists.

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 moderately lengthy but every sentence carries weight: purpose, input handling, output content, validation, confidence grading, and an example. It is front-loaded with the core action and then flows logically into supporting details. The structure is effective, though slightly verbose; it could trim some phrasing, but nothing is wasted.

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 tool with no output schema, the description provides a remarkably complete picture: it lists the return elements (labeled results, units, formula, citation URL), the confidence field's meaning, and a concrete example. An agent can confidently invoke this tool and understand what to expect. No significant gaps remain for correct invocation.

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% (both parameters and the nested inputs object are described), so baseline is 3. The description adds significant value beyond the schema by explaining how to reference input keys (field key or slugified label), that defaults are applied for missing inputs, and that validation occurs—details not present in the schema. This helps the agent construct valid and complete input objects.

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?

States a specific verb ('Run') and resource ('manufacturing calculation') and immediately clarifies what that means: executing a calculation with inputs and defaults, returning results, formula, and citation URL. It also distinguishes itself from sibling tools like get_calculator (which likely retrieves calculator metadata) and search_calculators (which finds calculators) by focusing on execution.

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?

Explains how to provide inputs (by field key or slugified label) and points to get_calculator for details. It explicitly mentions that missing inputs use defaults, giving the agent a clear path for validation. The example call further demonstrates usage. While it does not explicitly state 'use this when you want to perform a calculation,' that is strongly implied, and it effectively guides the agent on the prerequisites and expected flow.

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