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

Goes well beyond the annotations (readOnlyHint=false, idempotent=false, destructive=false) by disclosing token semantics (random possession proof, unsigned, not a password/API key/OAuth token), 24-hour unclaimed expiry, post-creation requirement of the workspace owner, that no collection or workspace is created, and a security warning not to expose the token.

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-loads purpose and return values in the first two sentences before layering security and lifecycle detail. Dense and slightly run-on with several clauses packed into single sentences, but essentially every clause carries operational value.

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?

Despite an output schema existing, the description still supplies lifecycle, security and follow-up-call context an agent needs to act correctly. For a zero-parameter, auth-sensitive bootstrap tool, nothing material is missing.

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?

The tool takes zero parameters, so the baseline of 4 applies and the schema has nothing to document. The description correctly spends no space on parameters and instead explains what to do with the returned values.

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+resource (start a preparation) and immediately names the two artifacts it produces, preparation_token and session_id, plus the auth modes it accepts. The opaque product term ('Jason preparation') and the fact that it never contrasts itself with any sibling keep it just below a 5.

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?

Gives clear context for invocation: OAuth vs anonymous WorkOS agent token, the note that anonymous tokens allow preparation only, and that the returned token is needed for request_work(workspaceless=true), get_conversation and cancel_work. It stops short of stating when NOT to use this tool versus an alternative entry point.

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