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

With no annotations provided, the description carries the full burden and does well: it explicitly declares the tool is read-only, explains that empty fields mean the value was not measured, and states error behavior for invalid input. This gives the agent critical behavioral context beyond basic invocation.

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 compact and front-loaded with the core purpose, followed by a high-value caveat about empty fields and then the read-only and error behavior. Every sentence contributes useful information, though the field list is slightly verbose and could have been more terse.

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 tool with one simple parameter and no output schema, the description covers the essential context: what fields are compared, how missing data is interpreted, that it is read-only, and what happens on invalid input. It does not describe the output structure beyond mentioning an error field, but that is a minor omission for such a straightforward 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?

The input schema already documents the single `ids` parameter with a clear description and range (2 to 6). The tool description mostly reinforces this by saying 'two or more things' and describing error cases for fewer than two ids, but it does not add substantial new meaning about the parameter itself. Baseline 3 is appropriate given 100% 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 clearly states the tool compares two or more items side by side on a specific set of fields: price, what goes in and out, what it needs, how it is called, and what was measured. This is more specific than a generic 'compare' statement signaling the resource and scope, though it does not explicitly differentiate from sibling tools like get_product or search_shelf.

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 important usage constraints: at least two ids are needed, unknown ids return an error, and empty fields mean 'not measured' rather than zero. However, it does not explain when to choose this tool over the many sibling tools, so the agent must infer the comparison use case from the name and title.

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