hires_upload_attachment

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

No annotations are provided, so the description carries full burden. It discloses object ownership verification ('strictly verified against the authenticated API key's company'), file size and type limits for voicemail, and the return shape `{uuid, url, file, relative_time}`. It does not cover failure modes or rate limits, but adds substantial behavioral context.

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, with a clear opening sentence and a dense but organized category breakdown. It packs a lot of information into two sentences without being verbose, though the first sentence is long. Front-loaded purpose makes 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?

The tool handles many categories and has a nested file object, but the description covers all key aspects: return format, category-specific rules, ownership verification, and special voicemail behavior. There is no output schema, so the described return value is essential. Minor gaps include error handling and size limits for non-voicemail categories.

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?

The schema already describes all parameters (100% coverage), so the baseline is 3. The description adds value by clarifying per-category object_id semantics (omit for voicemail), the default behavior of company_id (defaults to authenticated company), and the specific voicemail size/type constraints.

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 states the tool's purpose: 'Upload a file and create an attachment.' It lists supported categories, making the resource scope explicit. However, it does not explicitly differentiate from sibling tools like hires_upload_application_attachment, which could cause ambiguity.

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 context for each category, including when to omit object_id (voicemail) and how the returned uuid is used (nurture voicemail steps). It does not mention alternative tools or when not to use this tool, but the category breakdown gives strong usage guidance.

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