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

The description adds significant behavioral context beyond the annotations. It mentions that the tool is 'FREE' (no cost implications), which is not in the annotations. It explains the algorithm behavior ('Tries every rotation'), the return format (including 'rejected' field), and error behavior (never raises protocol errors, returns error objects). It also confirms read-only and idempotent nature, which aligns with the annotations, adding detail about retry safety.

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 well-structured with a clear opening statement, an example, usage guidance, and error handling. It is somewhat lengthy but each sentence serves a purpose. The first sentence is front-loaded and grabs attention. It could be slightly more concise, but the detail is justified for clarity, earning a 4.

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 tool is moderately complex with 5 parameters and an output schema, but the description provides comprehensive guidance: it explains the input format, gives a concrete example with expected output, clarifies the algorithm's behavior, and covers error cases. Since the output schema exists, the description does not need to explain return values in depth, but it does highlight the 'rejected' field, which is helpful. The description is complete for the tool's complexity.

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 covers all parameters with descriptions, and the description adds examples of typical input. However, the description provides additional context for the 'padding' parameter by explaining it as 'Cushioning allowance added to every item side' and mentions the default is 1.0, but it could go further in explaining units or implications. Since schema_coverage is 100%, the baseline is 3, and the description adds some extra value, so a 4 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 states the tool's purpose: 'Pick the smallest box an item actually fits in, allowing for padding.' It specifies the verb (pick), resource (box), and the key qualification (smallest, with padding). It distinguishes itself from siblings by explicitly noting it is not for carrier billing, which is 'dim_weight'. The example input/output further clarifies the function.

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 provides explicit guidance: 'Use when choosing packaging from stock. Not for what the carrier will bill once a box is chosen — that is dim_weight.' This clearly states when to use the tool and explicitly names an alternative tool (dim_weight) for a different scenario. It also mentions error handling and retry safety, which guides usage in failure cases.

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