Email documents

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

Annotations already mark the operation as open-world, non-read-only, and non-idempotent. The description adds meaningful behavioral context by stating 'This sends real mail to real people,' which emphasizes the real-world side effect and justifies the confirmation requirement. This goes beyond the annotation flags and is valuable for an agent deciding whether to call the 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?

The description is two sentences with no filler. The core action is front-loaded in the first sentence, and the critical safety warning is placed immediately in the second. Every phrase earns its place.

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 side-effecting email tool, the description covers the essential purpose, the real-world impact, and the key user-confirmation precondition. The absence of an output schema is acceptable because the tool's observable effect is the email itself. A minor gap is that the confirmation precondition lists recipients, subject, and body but omits explicit mention of confirming the documents to be sent.

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 40%, with `documents`, `subject`, and `message` lacking descriptions, but the tool description partially compensates by referencing 'one or more documents' and 'recipients, subject and body.' These phrases map to the main parameters and clarify their roles. However, `use_archive_version` is not explained anywhere, and no additional format or constraint details are added for the undocumented parameters.

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 opens with a specific verb and resource: 'Send one or more documents by email from the Paperless instance.' This clearly identifies both the action and the object. It also distinguishes the tool from sibling document operations by emphasizing actual email delivery, and there is no other email-sending sibling that could be confused with it.

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 a clear precondition: 'only call it after the user has confirmed the recipients, subject and body.' This tells the agent when it is appropriate to invoke the tool and explicitly warns against calling without user confirmation. It does not mention alternatives such as share links or bulk downloads, so it stops short of a full when/alternatives comparison.

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