Disputes add evidence

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

Annotations already indicate a non-read-only, non-idempotent operation, but the description adds valuable behavioral details: base64 encoding, per-item and per-dispute size caps, and authorization constraints. These go beyond the structured annotations and help the agent understand operational limits and permissions.

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 three concise sentences with no filler. The core action is front-loaded, followed by key constraints and authorization. Every sentence adds meaningful information, making it efficient for an agent to parse.

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 five parameters and no output schema, the description covers the essential operational context: the action, the state requirement ('open dispute'), size limits, and who can invoke it. It doesn't explain error handling or response format, but these are not critical given the schema coverage and lack of output schema.

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?

Schema coverage is 100%, so parameters are already documented. The description adds the per-dispute cap (not present in schema) and clarifies who can perform the action, providing extra context beyond individual parameter descriptions. This justifies a score above the baseline of 3.

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 action ('Attach an evidence item') and the resource ('to an open dispute'). It distinguishes this from sibling dispute tools (disputes_file, disputes_respond) by focusing on evidence attachment, and the verb is specific and unambiguous.

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?

It specifies the condition of an 'open dispute' and explicitly states who can upload ('Either the filing buyer or the seller-owner can upload'), giving clear usage context. However, it does not explicitly mention when not to use it or compare with alternative tools, though no direct alternative for evidence addition exists among siblings.

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