stripe_disputes_update

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

The description discloses critical behavior beyond the annotations: writing any evidence field submits every evidence field to the bank, submission is irreversible, and submit=false stages for review. These are exactly the side-effect and reversibility details an agent needs for a mutation tool.

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?

Two sentences, front-loaded with the core action and immediately followed by the critical side-effect warning. There is no wasted text.

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 irreversible side effects and no output schema, the description provides the essential safety context: default submission, staging via submit=false, and the all-fields submission behavior. The rich schema covers the evidence fields themselves.

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 the schema already documents parameters well. The description still adds important semantics: evidence fields are submitted collectively and submit controls staging versus immediate irreversible submission, which is not fully captured by the schema alone.

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 states a specific action and resource: adding evidence to a dispute. It is clear enough for an agent to distinguish from stripe_disputes_retrieve/list by intent, though it does not explicitly name those siblings or explain that this tool updates rather than reads disputes.

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 gives clear conditional guidance: set submit to false to stage evidence for review, otherwise submission happens automatically. It lacks explicit alternatives among sibling tools, such as using stripe_disputes_retrieve to review evidence before calling this one.

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