sezzle_diagnose_integration

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds the behavioral trait 'deterministic,' which is useful context beyond the annotations. However, it does not disclose what the output/report looks like or any other behavioral details, though the annotations cover the safety profile adequately.

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 a single, focused sentence with no redundant wording. It front-loads the key action ('Run deterministic Integration Doctor checks') and is appropriately sized for its broad purpose, even though it could include more detail without padding.

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 high complexity of the input schema, the absence of an output schema, and the large set of sibling diagnostic tools, the description is incomplete. It does not describe what the results/checks contain, how to interpret them, or how this tool relates to the targeted validators. An agent would lack critical context for proper invocation and result interpretation.

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 schema has 0% description coverage and only one complex nested parameter ('input'). The description provides a high-level categorical hint ('configuration, order, webhook, and reconciliation evidence') that maps loosely to the sub-parameters, but it does not explain the required fields, defaults, or how each piece of evidence is used. This is insufficient for an agent to construct a valid 'input' object on its own.

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 a specific action ('Run deterministic Integration Doctor checks') and the resource ('supplied configuration, order, webhook, and reconciliation evidence'). It accurately conveys what the tool does, but it does not explicitly differentiate itself from the many targeted sibling diagnostic tools, so it misses the highest level of clarity.

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?

There is no guidance on when to use this comprehensive diagnostic tool versus the more specific sibling tools (e.g., sezzle_detect_stuck_authorizations, sezzle_audit_auth_capture_flow). No prerequisites, exclusions, or alternative scenarios are mentioned, leaving the usage context entirely implied.

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