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

No annotations are provided, so the description carries full responsibility. The only behavioral claim is 'Expression discarded', which is nonsensical given the lack of an expression parameter. No side effects, permissions, or error behavior are disclosed; the description actively misleads about the tool's operation.

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 extremely short, which could be a virtue if accurate, but it is under-specified and misleading. It does not front-load useful information; it states a purpose that the schema cannot support. This is not conciseness but severe under-specification.

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 9 parameters, no output schema, no annotations, and a misleading description, an agent cannot determine how to call this tool correctly or interpret results. The description fails to bridge any gap between the tool's name and its actual behavior.

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?

Although the schema has 100% description coverage for its 9 parameters, the tool description adds no meaning to them and instead suggests a completely different parameter set (an arithmetic expression). The schema descriptions (e.g., 'Git ref name; discarded after the shape check') imply a generic shape-checking tool, not arithmetic. The description fails to align with the parameters, so it adds negative value.

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 claims 'Evaluate a+b style arithmetic' but the input schema exposes 9 unrelated string parameters (ref, url, city, feed, etc.) with no arithmetic expression field. This is misleading, not merely vague — an agent would have no way to supply an expression, and the stated purpose contradicts 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?

There is no guidance on when to use this tool versus any of the 26 siblings. The description does not mention alternatives, conditions, or exclusions. An agent gets zero help choosing this over, say, 'search-query-len' or 'validate-json'.

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