Holded inbox

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

No annotations are provided, and the description only names actions like delete, update, upload, and attach without explaining side effects, destructive potential, gating, or return behavior. The action names imply modification but do not disclose consequences or safety mechanisms.

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 compact sentence with no redundant wording. The action-to-parameter mapping is telegraphic but efficient, making it easy to scan.

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 multi-action dispatcher design, nested data object, and absence of an output schema, the description is too sparse to be fully actionable. It omits expected outcomes, error behavior, pagination details, and confirmation workflows.

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 description coverage is only 54%, and the description mostly repeats parameter names without explaining formats, allowed values, or the structure of the nested 'data' object. It adds little beyond what the schema already provides.

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 identifies the resource as 'Incoming documents scanned by Holded' and enumerates the supported actions, distinguishing this tool from the sibling Holded tools by resource domain. However, it does not explain the individual action semantics in any detail.

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 lists actions and their associated parameters but provides no guidance on when to choose one action over another, no workflow context, and no mention of confirmation requirements or pagination. An agent would have to infer usage from the action names alone.

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