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

Annotations already mark it as non-read-only and non-idempotent, so the description's job is lighter. It adds meaningful behavioral context: multiple files are zipped server-side into one bundle, both text and base64 are accepted, and the result travels as a single capability URL. It does not discuss authentication or expiration behavior, but those are partially covered in the schema.

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?

Three tight sentences front-load the trigger condition, then cover the two behavioral essentials (encoding support and zip behavior) and the most important alternative. The docs link is inline and unobtrusive; no word is wasted.

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 file-sharing tool with four well-documented parameters and annotations, the description plus schema covers trigger, payload encoding, bundle behavior, output as a capability URL, and the large-file alternative. No output schema exists, so the explicit mention of the URL result is valuable and sufficient.

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 75%, so the baseline is 3. The description adds value by clarifying the intended use of content_text versus content_base64 and explaining why bundle_name matters (multi-file zipping into one handoff). It does not deeply explain password or expires_days, but the schema already does that.

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 precise verb (share), a concrete resource (one or more files), and the target audience (another agent or person). It naturally separates from siblings like share_text and share_conversation by focusing on file bundles rather than text snippets or conversation histories.

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 opens with 'Use this when another AI agent... or a person needs access to one or more files' and then names the preferred alternative for large local files (HTTP API with link). This gives the agent a clear selection rule and an exclusion condition.

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