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

No annotations are provided, and the description doesn't disclose behavior beyond the vague 'Evaluate' and 'Expression discarded.' It doesn't mention side effects, error handling, performance characteristics, or any constraints on the input (e.g., max length, supported operators). The reader cannot infer what happens on invalid input or if the tool has any side effects.

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 (two short sentences), but the structure is poor. The first sentence is grammatically awkward ('Evaluate a+b style arithmetic') and the second is unclear. The description uses odd phrasing like 'Expression discarded' which is redundant with parameter descriptions. While not overly verbose, it is not well-structured for clarity.

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 tool has 9 parameters and no output schema, the description is extremely incomplete. It doesn't explain how the parameters relate to the tool's function, what the expected output is, or how this tool fits into the broader context of sibling tools like 'calculate' or 'math-eval'. The lack of clarity on the tool's purpose and parameters makes it nearly impossible for an agent to correctly invoke it.

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 covers 100% of parameters, the descriptions of the parameters are generic and seem copied from other contexts (e.g., 'Git ref name', 'HTTPS URL', 'City name'). The parameter descriptions do not relate to the stated purpose of evaluating arithmetic. For instance, 'query' says 'Search text; discarded after the length check' which contradicts the arithmetic purpose. The description doesn't explain how these parameters map to the tool's function, so the semantics are confusing and misleading.

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 'Evaluate a+b style arithmetic. Expression discarded.' is vague about what the tool actually does. It says 'Evaluate' but doesn't specify the verb clearly (e.g., 'calculate', 'compute'), and the resource is ambiguous. It also doesn't distinguish the tool from siblings like 'validate-json' or 'search-query-len' beyond the arithmetic hint, which is insufficient.

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 no guidance on when to use this tool versus alternatives. It doesn't mention scenarios, prerequisites, or exclusions. For example, it doesn't clarify that this tool is for arithmetic expressions only, not for search or validation, and doesn't reference sibling tools like 'validate-json' or 'search-query-len'.

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