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

With no annotations provided, the description must carry the full behavioral burden, but it only states 'Expression discarded.' This hints at non-retention but does not disclose what the tool returns, whether it mutates anything, what side effects occur, or what failure modes exist. The behavior is under-specified for an evaluator-style tool.

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 very short, but brevity comes at the expense of necessary information. 'Expression discarded' is an unclear fragment that does not clearly earn its place, and the whole text is closer to under-specification than efficient summarization.

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?

A tool with seven unrelated parameters and no output schema or annotations needs much more contextual explanation. The description does not identify which parameter carries the arithmetic expression, what the output looks like, or when this tool should be used. It is not minimally viable for an agent to invoke correctly.

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 adds no meaning to any of the seven input schema parameters, and it references an 'expression' concept that does not exist in the schema. An agent cannot map 'a+b style arithmetic' to any property like ref, url, city, feed, host, json, or path. This is a direct mismatch between the described API and the actual parameters.

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 says 'Evaluate a+b style arithmetic,' which names a verb and subject, but the input schema contains no arithmetic expression parameter—it lists ref, url, city, feed, host, json, and path. The sentence 'Expression discarded' is confusing rather than clarifying, because there is no expression field visible to the agent. This makes the purpose misleading despite the surface-level verb.

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, what kind of input to supply, or how it differs from sibling validation tools like validate-json, normalize-url, or file-path-ok. The description gives no context that would help an agent choose between alternatives. Only the tool name suggests arithmetic, which is not enough.

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