upload_attachment

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

Annotations already declare non-readOnly, non-idempotent, non-destructive, open-world behavior; the description adds the WRITE_ENABLED=true gate and the base64 encoding requirement, which are real value. It omits what happens on duplicate file names or oversized payloads at the tool level, and says nothing about the returned attachment identifier.

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?

Two tight sentences: the operation and its gating prerequisite come first, the use cases second. Zero 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?

With 100% schema coverage and annotations covering the mutation profile, the description is nearly complete. The one gap is that there is no output schema and no hint of what the call returns (presumably an attachment sys_id), which an agent would want in order to reference the uploaded file later.

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 100%, so every one of the five parameters is already documented in detail, including MIME examples and the 10 MiB decoded-size limit. The description only restates 'base64-encoded' and the record target, adding no syntax or format detail beyond the schema, so the baseline 3 applies.

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?

Specific verb plus resource plus target: 'Upload a base64-encoded attachment to a ServiceNow record'. It is unmistakably distinct from its siblings list_attachments, get_attachment_metadata, and delete_attachment, which read and remove rather than create.

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?

States the concrete use cases (files, screenshots, documents on incidents, changes) and a hard prerequisite, WRITE_ENABLED=true, that gates the call. It stops short of naming when not to use it or which sibling to prefer for retrieval, but the context is clear enough to route correctly.

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