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

With no annotations provided, the description carries the full burden of behavioral transparency. It discloses the return values, the meaning of each output component, and the expected item classes (base|worn|consumable). This exceeds minimal disclosure and gives the agent clear expectations of what the tool computes. It does not explicitly state side effects (e.g., persistence), but the read-only nature is strongly implied by the computation-focused verb and output.

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 two sentences, front-loaded with the action and resource, and packs essential details into a compact format. Every clause contributes: input structure, class meanings, and output components. There is zero fluff, making it easy for an agent to parse quickly.

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 simple (one parameter, no output schema), and the description fully covers what the agent needs: input format, class semantics, and the exact computed results. The absence of an output schema is compensated by listing the four output values. No additional behavioral notes are necessary for this straightforward calculation 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 single parameter 'items' benefits from the description's structural detail: '[{name, grams, qty?, class?}]' and the explicit class values. Although the schema already defines the properties, the description adds semantic meaning by explaining that 'class' dictates how weights are aggregated (base vs. worn vs. consumable) and that the output separates these categories. This goes beyond the schema's bare property definitions.

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 verb ('Sum') and resource ('gear pack items'), explicitly scoping the operation to grams. It distinguishes itself from sibling tools by being the only one that computes pack weight metrics, with specific output details (total, base weight, pack weight excluding worn, heaviest items).

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 implies its usage by defining the exact input format and output, making it clear when to invoke it. It does not explicitly state when not to use it or alternatives, but the specialized nature and sibling context leave little ambiguity. The return fields (e.g., 'base weight (the comparable number)') further guide correct usage for weight comparisons.

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