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

Annotations already declare readOnly, non-destructive, idempotent, and safe, so the bar is lower. The description adds 'Expression discarded', which hints that no durable effect or result is retained, but it still leaves the actual behavior unclear: the schema says inputs are used for shape checks, not arithmetic evaluation.

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?

Two sentences are concise, but the content is not appropriately scoped: it omits all operational detail for a tool with seven parameters. The second sentence, 'Expression discarded', causes confusion and does not earn its place.

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?

With no output schema and no return-value explanation, the description needed to explain what the tool returns or confirms, how an expression is supplied, and which arguments are valid. It does none of this, and its arithmetic framing is incompatible with the schema, leaving the tool effectively uncallable from the description alone.

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 seven parameters, so the schema alone is informative. However, the description introduces an 'expression' that is absent from the schema and says nothing about which of ref/url/city/feed/host/json/path should be supplied, making parameter selection harder rather than easier.

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 claims a specific purpose, 'Evaluate a+b style arithmetic', but the input schema has no expression parameter; its seven string parameters are all unrelated shape checks and hints. This is misleading: an agent cannot tell that the tool cannot actually do arithmetic, and 'Expression discarded' undercuts the stated purpose.

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 when-to-use or when-not-to-use guidance is provided, and no alternative tools are mentioned. The agent is given no basis for choosing calc-eval over siblings such as validate-json, domain-shape, or weather-hint.

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