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

Beyond the annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false), the description discloses the key traits an agent cannot infer from structured fields: the link is single-use, expires in one hour, must be handed to the person rather than opened, and degrades gracefully to a normal dashboard link on a full account. Those are exactly the operational facts that determine correct invocation here.

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 precondition is front-loaded and each subsequent sentence adds a distinct operational rule (destination targeting, expiry, don't-open-yourself, fallback behavior), so nothing is wasted. The first sentence is slightly padded with 'with everything in it', but the density of actionable content is high.

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?

There is no output schema, and the description compensates by describing what is returned in both the guest case (a one-time link) and the full-account case (a normal dashboard link). Combined with the expiry and handling rules, an agent has everything needed to call it and act on the result correctly.

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 0%, so the description has to carry the burden, and it does explain the purpose of the id parameters — they select the destination the recipient lands on — while implying the alternatives are choose-one. It does not explain the remaining 'page' enum members (editor, runs) or note that all four parameters are optional, so a gap remains against a four-parameter schema with no field documentation.

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 states a specific verb and resource — produce a one-time invitation link that lets a guest create an account or sign in and retain the workspace — and frames it with an explicit precondition ('For a guest account (whoami says guest)'). That precondition, plus the named sibling behavior of whoami, lets an agent distinguish it from link-producing tools such as get_upload_link or get_share.

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?

It states when to use it (guest account), how to target it (name a workflow_id, agent_id or run_id, or page: logs, so the recipient lands on what they asked to see), and an explicit prohibition ('Give the person the link; never open it yourself'). It also covers the repeat case ('ask again for a new one') and the non-guest case (returns a normal dashboard link), leaving little to inference.

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