percent_change

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

Annotations already declare readOnly and idempotent behavior, so the description does not need to restate those. However, it introduces ambiguity by listing three possible calculations (percent change, markup, margin) without explaining how the tool decides which to compute or what output format to expect. This is a significant behavioral gap not covered by annotations.

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, well-structured sentence that immediately states the tool's purpose without any filler. It is front-loaded and concise, earning a perfect score for this dimension.

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?

While the tool is simple and parameters are well-documented, the lack of output schema and the ambiguous listing of three separate metrics make the description incomplete. It would be more helpful to specify what the function returns (e.g., the percentage value) and any conventions like sign handling. Given the annotations and schema, a score of 3 reflects a minimally viable but not enriched description.

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%, with 'old_value' and 'new_value' clearly described as starting/original and ending/new values. The description adds no additional meaning beyond the schema, so the baseline of 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 clearly specifies a calculation verb ('calculate') and the resource ('percent change, markup, or margin') between two values. It conveys a distinct purpose, though it could more strongly distinguish itself from sibling tools like 'gross_margin' by noting that all three metrics are returned or selectable.

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 offers no guidance on when to use this tool versus alternatives such as 'gross_margin' or 'calculate'. It does not state any exclusions, prerequisites, or typical use cases, leaving the agent without context for tool selection.

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