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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description goes further: it states the effect 'cannot be undone from here', that pretix applies its own refusal rules and returns the reason, that it never forces a check-in, and that unanswered required questions come back as incomplete with a question list. These are exactly the failure modes an agent needs to anticipate for a destructive write.

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?

Tight, front-loaded prose: capability, irreversibility, identification, then edge cases. The trailing raw endpoint is the only sentence of marginal utility for an agent, but it does confirm the exact scope of the operation.

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?

With no output schema, the description carries the burden of describing responses and does so for the error paths (refusal reason, incomplete + question list) but not the success payload. Given a destructive, rule-heavy write operation, this is well covered short of the success shape.

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%, so the baseline is 3, but the description adds real semantics: it explains the position_id vs ticket_secret trade-off, that one ticket per call, and that `answers` is used to resolve the incomplete response. The `type` (entry/exit) parameter is only hinted at via 'in (or out)', leaving one minor gap.

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?

Opens with an explicit verb and resource ('check one ticket in (or out) on a check-in list') and marks it as a WRITE operation, which cleanly separates it from all the pretix_list_* and pretix_get_* siblings. An agent can tell immediately that this is the only mutation tool in this family.

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 names where position_id comes from (pretix_list_checkin_list_positions) and offers ticket_secret as the alternative identification path, plus concrete refusal conditions (unpaid, canceled, blocked, already-used, wrong-product). What it lacks is an explicit statement of when NOT to call it (e.g. when a list is not in redemption mode), but the implied context is clear.

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