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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds no behavioral context beyond that — nothing about error behavior for malformed expressions, computation limits, or how non-terminating results are returned.

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 short sentences with the core capability front-loaded. The second sentence is marginal (endpoint equivalence rather than capability detail) but costs little and is not padded.

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 only two well-documented parameters and annotations covering safety, most of what an agent needs is present. However, there is no output schema and the description does not describe the return shape (e.g., exact rational vs. rounded decimal string), which is the one remaining gap for a computation 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?

Schema description coverage is 100%, and the schema already documents the expression syntax, URL-encoding of '+', and the digits default/max, so the description carries no additional parameter meaning. Per the baseline rule for full coverage, 3 is appropriate.

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 the resource and the distinguishing property ('exact rational arithmetic with no floating-point error'), which cleanly separates it from the math-adjacent siblings dateMath, countText and textStats. It is clear what the tool computes, though it never uses an explicit verb like 'evaluate' or says the input is a string expression.

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 (e.g., dateMath for temporal arithmetic, or a floating-point path elsewhere), and no stated exclusions or prerequisites. The only usage-adjacent line points at an external HTTP endpoint rather than helping an agent decide to call this tool.

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