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

No annotations are provided, so the description carries the full burden. It states 'Expression discarded', but no expression parameter exists in the schema, and it does not disclose side effects, return value, validation behavior, or what happens to the listed fields. The behavioral clue is therefore more confusing than informative.

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 two sentences are short and front-loaded, but they sacrifice necessary specification. For a 9-parameter tool with no output schema, this is under-specification rather than conciseness. Each sentence is present but not informative enough to support correct invocation.

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 nine parameters, no annotations, no output schema, and a sibling list dominated by shape-check tools, the two-sentence description is far from complete. It omits what the tool returns, which input should be supplied, and how the fields are validated or discarded. The mismatch between description and schema makes the missing context critical.

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 schema coverage is 100% and each property has a description, the tool description adds no parameter meaning and actually references a non-existent 'expression'. It does not explain how ref, url, city, feed, host, json, path, zone, or query relate to 'a+b' arithmetic. The phantom expression undermines the otherwise self-describing schema.

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 resource, but the input schema contains no expression parameter—instead it lists ref, url, city, feed, host, json, path, zone, and query, all described as discarded or checked values. This mismatch makes the tool's actual purpose unclear and fails to distinguish it from the many sibling shape-check tools. An agent cannot reliably know what calc-eval operates on.

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 text explains when to use calc-eval versus siblings like domain-shape, file-path-ok, validate-json, or normalize-url. The 'arithmetic' hint implies mathematical use, but the parameters are unrelated to arithmetic, so any implied usage is misleading. No exclusions or alternatives are mentioned.

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