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

Annotations already declare destructiveHint=true, but the description provides substantial additional context: changing priceCents from 0 to >0 instantly blocks check-in for ticketless users and disconnects already-registered attendees; disabling onlineEnabled also kills the live stream, join_activity_online, and free-event 'visible only after signup' materials; and ensure_activity_live may silently reset it to true in certain conditions. This is exactly the kind of side-effect awareness an agent needs and goes far beyond the annotation.

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 description is well-structured with clear labels: 【需要登录】【何时用】【组合链】【口径/坑】. Each section carries essential information without redundancy. The critical warnings are front-loaded and the phrasing is dense yet precise. Every sentence earns its place, and the format makes it easy for an agent to parse.

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 destructive, parameter-rich tool with no output schema, this description covers the essential context: authentication requirement, when to use it, recommended pre-call (get_organizer_ticketing), return behavior ('返回体即新现值'), major side effects with explicit error codes, and shop restrictions. An agent is well-equipped to call this tool safely and correctly. Minor details like exact error format are absent, but the description provides more than enough for safe invocation.

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 only 11% (only activityRef has a description). The description adds a valuable partial-update semantic ('省略的字段不改' – omitted fields are not modified) and highlights the special side effects of priceCents and onlineEnabled poverty. However, it does not explain the meaning or usage of the other seven parameters (e.g., listPriceCents, grantsAnnualPassDays, ticketContactUrl), leaving a significant gap that the low schema coverage does not fill.

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 ('改' = update) and a specific resource (ticket and online participation configuration for organizers), with clear examples of what is changed: price, seats, ticket note, or toggling online attendance. It is distinct from the many sibling tools by focusing on organizer ticketing configuration, and even references the companion read tool get_organizer_ticketing, making the purpose unambiguous.

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 description explicitly includes an '【何时用】' section that defines exactly when to use this tool (when the organizer wants to modify pricing/seats/ticket notes or toggle online participation), and it states that omitted fields are not changed wat does this mean? It also notes the non-negotiable precondition of confirming each change with the user. It gives an exclusion (non-self-operated activities return an error and are not retryable), but does not explicitly compare with alternate tools like update_activity, so it falls just short of a 5.

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