计算

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

Given there are no annotations, the description carries the burden of transparency. It declares the core behavior (computing an average) and, being a pure calculation with no side effects, nothing more is required. The existence of an output schema covers return format, so the description is sufficiently transparent.

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 a single, concise sentence that immediately states the tool's purpose. It contains no filler words or redundant details, making it optimally front-loaded and easy to scan.

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?

For a simple, deterministic calculation, the description, combined with the input schema (which defines the three number parameters) and the presence of an output schema, is fully complete. There are no hidden prerequisites, side effects, or complex behaviors that require additional explanation.

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 input schema has no descriptions for a, b, c, and the description only states that they are 'three numerical values.' This adds little beyond the 'number' type already present in the schema, but since the average is order-invariant, not distinguishing parameters is acceptable. The description provides minimal compensation for the 0% schema coverage.

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 uses a specific verb ('计算' / calculate) and identifies the exact resource ('三个数值的平均值' / average of three values), clearly distinguishing it from sibling tools like evaluate_score and get_student_name. It precisely states the tool's function without ambiguity.

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 implies usage (when you need to average three numbers) but provides no explicit guidance on when to prefer this tool over alternatives, nor any exclusions. The intended use is obvious from the purpose, but this dimension requires more explicit context for a higher score.

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