Dispose as theft/loss

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

The description adds valuable behavioral context beyond the annotations: it states that dry-run is the default and that confirm:true is required to execute, making the mutation behavior explicit. The trailing 'Write.' reinforces that this is a write operation. While it doesn't detail consequences or reversibility, the dry-run/confirm mechanism is a strong transparency feature that goes beyond the sparse 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 extremely concise: four short sentences totaling under 30 words. It front-loads the main purpose, then adds essential safety and validation details. Every sentence earns its place, with no filler or redundancy.

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 mutation tool with 10 parameters and no output schema, the description provides only minimal context. It covers the core action and the critical dry-run behavior but does not explain what happens on commit (e.g., if items become unavailable), what the response contains, or how this tool relates to other disposition tools. The schema covers 60% of parameters, but the description alone leaves gaps in overall completeness.

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 description adds meaning for key parameters: 'Provide discovery date and incident numbers' likely maps to theftLoss_DiscoveredDate and the incident number fields, and 'pass confirm:true' clarifies the confirm parameter. However, with 60% schema coverage and 10 parameters, the description does not fully compensate for the remaining undocumented parameters, and it slightly conflates the required 'date' with the discovery date.

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 starts with a specific verb-resource pair: 'Record and commit a theft/loss disposition for inventory items.' It clearly identifies the tool's unique scope (theft/loss) and distinguishes it from sibling tools like dispose_destroyed and dispose_nfa. The additional mention of discovery date and incident numbers further refines its purpose.

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 usage for theft/loss dispositions and provides a clear usage hint about dry-run vs. confirm. However, it does not explicitly state when to use this tool versus alternatives like dispose, dispose_destroyed, or dispose_nfa. The guidance is inferred from the name/title rather than articulated.

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