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

The annotations declare readOnlyHint=false, destructiveHint=true, and idempotenceHint=false, but the description never discloses what destructive or non-idempotent behavior occurs. 'Expression discarded' adds a small retention clue, but 'Evaluate' sounds like a pure read-only computation, which conflicts with the annotated destructive profile. There is no explicit contradiction strong enough to flag, but the behavioral disclosure is clearly inadequate.

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 text is short, which is superficially concise, but it is under-specified rather than efficiently specified. 'Expression discarded' is unhelpful because no expression parameter exists, and the brevity comes at the cost of omitting essential purpose and behavior information.

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?

This tool has seven heterogeneous parameters, no output schema, and annotations indicating destructive behavior, yet the description supplies almost none of the context needed to call it correctly. An agent cannot determine expected inputs, outputs, side effects, or appropriate invocation scenarios.

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 coverage is 100%, so the baseline is 3, but the description actively harms parameter understanding by referencing 'a+b style arithmetic' when no such parameter exists. The schema descriptions themselves are the only useful signal, and the description adds no meaningful linkage to them.

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 the tool evaluates 'a+b style arithmetic', but the input schema exposes seven unrelated parameters (ref, url, city, feed, host, json, path) and no expression or operand field. This is actively misleading: an agent cannot tell what calc-eval actually does with these inputs, and the stated purpose is unsupported by the schema.

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?

The description gives no guidance on when to use this tool versus its many siblings, and no conditions or alternatives are mentioned. Worse, the only implied use case—evaluating an arithmetic expression—is impossible given the schema, so the guidance is misleading rather than merely absent.

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