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

Annotations only say this is not read-only and not destructive; the description adds the material behavioral facts: the link is PUBLIC, it is scoped to a contact, it expires, and the agent is responsible for delivery. That public-exposure disclosure is exactly the kind of context annotations cannot convey. It stops short of saying how long the expiry is, whether the link is single-use, or whether generating a new link revokes an old one.

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 short sentences, front-loaded with the action and its purpose, then the return value, then the operational caveat. No filler and nothing repeated from the schema.

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 one-parameter tool with no output schema, the definition covers purpose, the return value (URL and expiry), and who delivers the link. The remaining gap is link lifecycle detail – expiry duration and revocation behavior – which matters for a public, externally shared artifact but is not strictly needed to invoke the tool.

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 coverage is 100%, and the schema already documents contactId as a UUID with a pointer to search (scope contacts) and a warning that it is not a phone number. The description adds nothing further about the parameter, so this is the baseline case where the schema does all the work.

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 ('Generate a public upload link for a contact') plus the file types it accepts, so the agent knows exactly what capability this exposes. It also implicitly carves out that delivery is the caller's job ('Send the URL ... yourself'), which separates it from sendSms, though it never names a sibling tool outright.

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 context of use is clear: a contact needs to attach files and the agent must hand them a link externally. The 'yourself' clause usefully signals that a separate messaging step is required, but there is no explicit when-not guidance (e.g. for existing files use list_customer_files) or stated prerequisites beyond the contactId.

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