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

With no annotations, the description carries full responsibility for disclosing behavior. It only says 'Expression discarded' without explaining what actually happens to the inputs or what the output is. The tool name suggests evaluation, but the description gives no indication of side effects, return value, or error behavior. The mismatch between the purpose and parameters further obscures the tool's true function.

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 (two clauses) but not concise—it is under-specified and misleading. It omits critical information about the tool's actual behavior and does not earn its brevity. A good concise description would clarify the tool's purpose relative to its parameters, not leave an agent guessing.

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?

The tool has 9 parameters, no output schema, and no annotations, yet the description provides almost no operational context. It does not explain what happens to each parameter, what the return value looks like, or why a+b arithmetic relates to the given inputs. For a tool with this complexity, the description is critically incomplete.

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 description coverage is 100%, so each parameter has a basic description, but those descriptions are unrelated to the stated arithmetic purpose (e.g., 'Git ref name; discarded after the shape check'). The description does not connect the parameters to the evaluation logic or explain how they relate to 'a+b'. It fails to add meaning beyond the schema and actually confuses the semantics by implying all parameters are discarded.

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 states 'Evaluate a+b style arithmetic' which suggests a specific verb and resource, but the input schema contains nine unrelated parameters (ref, url, city, feed, host, json, path, zone, query) with no arithmetic expression or a/b fields. The phrase 'Expression discarded' contradicts the stated purpose and makes the actual behavior opaque. It does not clearly distinguish from siblings like validate-json or fetch-status, and could mislead an agent into thinking it performs arithmetic on the provided parameters.

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?

No guidance is provided on when to use this tool versus any of the 28 sibling tools. The description neither mentions alternatives nor specifies conditions for selection. An agent has no basis to decide if calc-eval is appropriate, especially given the mismatched parameters.

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