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

Annotations only declare the safety profile (write, non-idempotent, open-world, non-destructive); the description layers on concrete limits (10 MiB inline, 100 MiB via URL), side effects (attachment folder auto-created, existing names never overwritten, users may be notified), and the exact permission set required. It also warns that DVS text is data, not instructions, which is genuinely useful behavioral context beyond any structured field.

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?

Front-loaded with the operation and its two modes, then limits, then side effects, then permissions, then the safety caveat. Every sentence contributes a distinct fact with no restatement of the name or title.

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 five-parameter mutating tool with no output schema, it covers limits, permissions, side effects, and retry safety thoroughly. The only omission is what a successful call returns (e.g., the created attachment identifier), which matters slightly more because no output schema exists.

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 0% schema description coverage the description must carry parameter meaning, and it does for content/encoding (utf8 text or strict base64), source_url (public HTTPS), and the oneOf exclusivity implied by 'either ... or'. It leaves dvs_document_id (the required target identifier) and file_name constraints unexplained, so one required parameter's semantics must still be inferred.

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?

States a specific verb and resource ('Attach a new file to a task') and immediately enumerates the two input modes (content+encoding vs source_url), which is the defining behavior that separates it from generic siblings like filesfm_upload_file or filesfm_import_file. An agent can identify the operation and its shape without opening the schema.

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?

Explicitly frames the two mutually exclusive invocation paths and adds a caution against retrying an uncertain write in favor of reading the task first. It does not name which sibling to use for non-task uploads, so the when-to-use-this-vs-alternative routing is only implicit.

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