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

No annotations are present, so the description must fully disclose behavior. The phrase 'Expression discarded' conveys that the expression input is not retained, but the schema offers no place for an expression, and the actual parameters (ref, url, city, etc.) are said to be 'discarded after' checks. This minimal transparency does not clarify side effects, security, or output behavior, leaving major gaps.

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 only two short sentences, which is concise and front-loads the action. However, the extreme brevity sacrifices essential information, and the structure provides no connection to the actual schema fields. It is not verbose, but it is under-specified for a tool with 15 input parameters.

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?

Given the absence of annotations, no output schema, and a large input schema that conflicts with the description, the description is completely inadequate for an agent to select and invoke the tool correctly. The description fails to explain how to provide the arithmetic expression, what the input parameters are for, or what to expect after calling the tool.

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 description does not map any input parameter to the promised arithmetic expression. The schema's parameter descriptions are individually clear but describe unrelated validation tasks (e.g., 'Git ref name... discarded after the shape check', 'JSON text to validate'). The description adds zero meaning to these parameters and instead implies an expression parameter that does not exist, actively misleading parameter selection.

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 mentions a specific action ('Evaluate a+b style arithmetic') but the input schema contains 15 properties (ref, url, city, feed, host, json, path, etc.) that are unrelated to arithmetic and instead describe various validation/normalization checks. This mismatch makes the tool's actual purpose confusing and does nothing to distinguish it from siblings like validate-json or normalize-url. It is not a pure tautology, but it is misleading.

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 gives no guidance on when to use this tool versus its many siblings. It only says 'Evaluate a+b style arithmetic' and 'Expression discarded,' which does not explain the context of use or any alternatives. There is no mention of prerequisites, exclusions, or typical scenarios.

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