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

'Expression discarded' does disclose a non-persistence behavior, but it conflicts with the schema's actual parameters and there is no mention of what the tool returns, side effects, or failure modes. With no annotations provided, the description carries the full transparency burden and falls well short.

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 in word count but that brevity is not earned—one fragment and one vague sentence that together misrepresent the tool. It is under-specified rather than concisely structured, and both sentences fail to align with the schema.

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 seven parameters, no annotations, and no output schema, a two-clause description that ignores all parameters and specifies no return value is almost entirely inadequate. An agent cannot infer how to construct a valid call, what the result looks like, or when this tool applies.

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 never refers to the seven schema parameters, and the phrase 'a+b style arithmetic' implies an input (an expression) that does not exist in the schema. This actively misleads an agent about the required inputs, making the description worse than simply providing no parameter information.

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 a specific operation, 'Evaluate a+b style arithmetic', which sounds like a calculator, but the input schema contains no arithmetic expression parameter—only ref, url, city, feed, host, json, and path. The stated purpose cannot be acted on with the provided schema, and it does not differentiate itself from sibling tools like validate-json or domain-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 this tool versus alternatives, no exclusion conditions, and no context about the intended workflow. The sentence provides only a vague operation and a note that an expression is discarded, which offers no decision support.

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