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

Beyond the annotations (read-only, idempotent), the description discloses crucial behavioral details: it never raises protocol errors and instead returns an error object, it is a heuristic rather than optimal, fragile items carry nothing, and min_support defaults to 0.6. It also explicitly confirms read-only and idempotent behavior, making retries safe. This is exceptional transparency.

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 long but information-dense, and the useful details (example, rotation rules, error behavior, heuristic status) each earn their place. The example JSON is heavy but instrumental for correct invocation. Slight deduction for the trailing 'FREE.' being low-value and the overall length being near the upper bound.

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 packing tool with nested objects and non-obvious constraints, the description is nearly complete: it covers input semantics, output shape via example, error format, retry safety, heuristic limitations, and special rules. The presence of an output schema reduces the need to explain return values, and the description still supplies a concrete example. Nothing critical is missing.

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?

Although the schema already covers 100% of parameters, the description adds substantial meaning: a full example input/output, the meaning of 'rotation per item' (any/upright/fixed), the 'rules.min_support' default, the interpretation of 'fragile', and that containers are 'used in the order given'. This goes well beyond the schema's brief property descriptors.

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 first sentence states a specific verb and resource: 'Place up to 20 boxes into containers or pallets with rotation, weight and support rules.' It also scopes the tool by the size cap and adds a concrete decision purpose ('decide pallet or carton count before booking freight'). This clearly distinguishes it from siblings like pack_bins_large even without naming them.

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 a clear use case: 'Use to decide pallet or carton count before booking freight.' It also warns that the algorithm is a 'first-fit-decreasing heuristic' and not proven optimal, which helps set expectations. However, it does not explicitly state when not to use this tool or mention pack_bins_large as the alternative for larger problems, so it falls just short of full alternative guidance.

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