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

Annotations already provide readOnlyHint=false and destructiveHint=false, and the description only restates the mutation by saying 'upload.' It adds no information about file size limits, overwrite behavior, permissions, or what response the caller should expect, which matters for a write operation.

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 efficient sentence with no filler. It front-loads the action and encoding requirement, making it easy to scan, though it under-specifies important details.

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 tool with a nested file object and no output schema, this description is incomplete. It does not state that 'id' refers to an application, what input restrictions exist (e.g., max size, supported mime types), or what success/failure looks like, leaving important operational gaps.

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 0%, the description must clarify the parameters, but it only mentions that the file is base64-encoded, which partially hints at the 'data' field. It does not explain that 'id' is the application ID, nor does it address 'file_name', 'mime_type', or 'size' semantics beyond what a developer might guess.

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 states a specific verb and resource: 'upload a base64-encoded file as an application attachment.' This distinguishes it from broader sibling tools such as hires_upload_attachment and hires_upload_candidate_file, though it does not explicitly name the alternatives or their differences.

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 tool versus hires_upload_attachment or hires_upload_candidate_file. No context is provided about prerequisites, such as needing an existing application ID or when a candidate file upload would be more appropriate, so agents are left to infer usage.

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