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

The description discloses many behaviors beyond annotations: replacement semantics ('uploading a second document for the same requirement replaces the first'), ephemeral deletion ('source and output documents are deleted 60 to 70 minutes after the last activity'), cost implication ('attachments are part of the already-billed prepare'), and file type/limit constraints. This is rich, actionable context that annotations do not provide.

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 long and includes a misleading first sentence that is tangential to the tool's purpose. While every subsequent sentence adds value (constraints, replacement, ephemeral, billing), the lack of front-loading of the core action and the confusing opener hurt structure. It could be tightened.

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?

The description covers most operational details: file sources, types, limits, requirement behavior, retention, and billing. However, it does not explicitly state that at least one of file_url or file_base64 must be provided, which is a critical requirement given the schema makes both optional (default null). The presence of an output schema reduces the need to explain return values.

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 0%, so the description must explain parameters, and it does thoroughly: file_url is a public https link, file_base64 is an alternative, proposal_id refers to a proposal from prepare_form, and requirement names an entry in the form's attachments_required list. This fully compensates for the schema's lack of descriptions.

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 core action is clearly stated: 'Attach one document ... to a proposal from prepare_form.' However, the description begins with a confusing preamble about 'Prepare a form from documents' which seems to belong to a different tool, muddying the primary purpose. The verb+resource is specific, but the opening reduces 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?

The description implies usage (attach documents to a proposal) and gives constraints (file types, limit, requirement replacement), but it never explicitly contrasts with sibling tools like fill_form, commit_proposal, or prepare_form. No when-to-use vs. alternatives or when-not-to-use guidance is provided.

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