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

With no annotations, the description carries the full behavioral burden, but it only says the expression is discarded and gives no return value, side effects, permissions, or failure behavior. 'Expression discarded' hints at behavior but is too terse and unclear to be actionable.

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 short and front-loaded, with no wasted words. It is under-specified for the tool's apparent complexity, but it is not verbose or poorly ordered; the sentences both carry some content.

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?

Despite having seven parameters, no annotations, no output schema, and many closely related sibling tools, the description provides almost no contextual information: no return shape, no typical inputs, no relationship to sibling tools, and no indication why the schema parameters are relevant. It is not enough for an agent to reliably select or invoke the tool.

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 schema descriptions cover all parameters, so a baseline of 3 would normally apply; however, the description introduces an 'expression' concept that maps to no schema property, and the listed parameters (ref, url, city, feed, host, json, path) are all described as shape checks unrelated to arithmetic. This mismatch makes the description actively confusing rather than semantically helpful.

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 the tool evaluates 'a+b style arithmetic,' which is a specific verb and resource, but it is undermined by the schema, which contains no arithmetic expression parameter and instead lists unrelated shape-check fields. The phrase 'Expression discarded' adds ambiguity about whether the tool actually evaluates or merely checks a shape.

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 calc-eval instead of the many sibling shape-check and validation tools, nor any exclusions or prerequisites. Usage must be inferred entirely from the short arithmetic phrase.

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