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

While annotations confirm safety (readOnlyHint: true), the description adds vital behavioral context by specifying that the diff is precomputed. It sets expectations regarding availability, noting that the bill must have more than one text version to return a diff.

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 tool packs significant technical and workflow information—input source, parameter roles, and output format—into a concise, front-loaded paragraph without unnecessary filler.

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?

The description is complete, providing all necessary context: how to acquire the input IDs, the roles of the parameters (`from` vs. `to`), and the specific types of analysis the tool performs.

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?

Since schema coverage is 100%, the description focuses on adding semantic context. It clarifies the necessary prerequisite workflow for obtaining the `from` and `to` parameter values, which is essential for agent execution.

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 is highly specific, stating that it compares two versions of a bill and listing the exact metrics provided in the output (unified diff, similarity, line/character counts, and highlights). It clearly distinguishes this function from simple text retrieval tools.

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?

It provides explicit workflow instructions, noting that the version IDs must first be retrieved from the `get_bill` tool with the `include:['texts']` flag. It also defines the temporal relationship between the `from` and `to` parameters.

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