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

Beyond the annotations (which already declare non-read-only, idempotent, non-destructive, open-world), the description discloses the two distinct outcome paths: a payment link where the case only becomes active after payment, versus an access-code path yielding an active case. That is real behavioral context an agent cannot infer from structured fields.

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?

Two sentences, front-loaded with the action and its prerequisite. The second sentence is dense with return-value detail but every clause carries information about the divergent outcomes.

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?

Covers the prerequisite step, the human confirmation gate, and both post-call states. Return values are additionally explained despite an output schema existing, so nothing critical for correct invocation 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?

Schema description coverage is 100%, so both parameters (confirmation_token, idempotency_key) are already fully documented, including the 15-minute validity and retry semantics. The description only restates that the token comes from the prepare step, which the schema already conveys.

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 ('Opens the case') and ties it to the artifact produced by a named sibling step ('prepared with a confirmation_token'), so an agent can distinguish it from sos_prepare_case and sos_get_case without opening any 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?

Gives a clear precondition sequence: the case must have been prepared and the traveller must have confirmed it before this call. It does not explicitly name an alternative or a when-not case, but the ordering against sos_prepare_case is unambiguous.

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