didit_session_update_data

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

The description adds behavioral context beyond minimal annotations: it clarifies the operation is a mutation for reviewer override and that only specified fields are updated. While annotations only convey non-read-only and non-destructive, the description omits potential side effects like triggering re-verification or downstream impacts.

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: a concise action-resource statement and a clear usage instruction. It is front-loaded with the primary purpose and contains zero superfluous words.

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?

Given the tool's complexity (18 parameters, nested objects, output schema), the description lacks important context about post-update effects, permanence, session state requirements, or any triggers. Even though an output schema exists, the brief description does not adequately cover the operation's implications.

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?

With only 33% schema description coverage, the description should compensate but only provides a general instruction to send only changed fields. It does not elaborate on individual parameters such as date formats, enum meanings, or the purpose of nested objects, leaving much ambiguity for the agent.

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 'Correct' and the resource 'KYC data extracted from the ID document on a session', specifying it's a 'reviewer override'. It distinguishes the tool as a partial update operation, setting it apart from other session tools like create or status updates.

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 provides clear usage context: 'Only send the fields you want to change' indicates a partial update pattern. It also implies reviewer use via 'reviewer override'. However, it does not explicitly mention when not to use or list alternatives among the many sibling session tools.

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