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

The annotations already declare readOnlyHint:false and destructiveHint:false, so the description does not need to restate that this is a write operation. The description adds valuable behavioral details beyond annotations, such as the 5MB and 25MB size limits, the requirement to include url on every hosted call, and the fact that api_base_url is ignored on hosted. These specifics help an agent anticipate behavior without relying on annotations alone.

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 concise, using only three sentences. It front-loads the main purpose and then packs in usage constraints efficiently. Every sentence contributes essential information—purpose, parameter selection, and size limits—without redundancy or filler.

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 has 9 parameters and no output schema, the description explains the main execution modes and size limits, but it does not describe the return value, success/error indicators, or how to handle failures. It also leaves several parameters unexplained. While the description covers the core usage well, the absence of output semantics and some parameter details makes it only partially complete.

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 schema description coverage at only 44%, the description compensates by clarifying key parameter relationships: content_base64 for hosted, file_path for local, filename defaulting to basename, and api_base_url being local-only. It also explains size constraints tied to these parameters. This adds significant meaning beyond the raw schema, though some parameters (task_id, session_id, mime_type) remain under-explained.

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 uses a specific verb ('Upload') and a clear resource ('requested applicant document'), making the tool's purpose immediately obvious. This clearly distinguishes it from siblings like submit_intake or save_intake_draft, which focus on other actions. The phrase 'requested applicant document' also suggests a precise context, enhancing 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 provides clear guidance on how to use the tool in different environments (hosted MCP vs. local stdio) and which parameters to use accordingly. However, it does not explicitly mention when to use this tool over alternative tools, or when not to use it, leaving some ambiguity for an AI agent. The environment-specific instructions are useful but not a full replacement for explicit usage boundaries.

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