anon_patch_finance_ticket

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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds context the annotations cannot: the required finance:manage permission, the fact that saving ticketTypes clears the old single-ticket fields (a concrete disclosure of what gets destroyed), and that the response shape varies with the request body. It stops short of describing permissions/rate-limit edge cases or error behavior.

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-loaded with purpose and permission, then the two body modes with their side effect, then the endpoint and the note that projectId is auto-derived. Every sentence carries distinct information; the endpoint line is the only mild redundancy but aids precision.

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 nested-body mutation with no output schema, it covers auth, side effects, body modes, and project auto-scoping, which is most of what an agent needs. It notes the response shape is request-dependent but never sketches either shape, leaving some ambiguity before 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?

Top-level schema coverage is 0% (the body object itself is undocumented), so the description carries real weight: it names both body shapes, maps ticketTypes to the multi-type array (0~20) and ticketPrice+ticketCount to the legacy shape, and flags the field-clearing interaction. It does not enumerate individual nested field constraints (price precision, name maxLength), so it doesn't fully close the coverage 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?

States a specific verb+resource (设置门票 = set/configure the finance ticket) and gives the concrete endpoint PATCH /api/projects/{id}/finance/ticket. The agent can tell it is a ticket-configuration write, distinct from anon_get_finance/anon_post_finance, though it never explicitly differentiates itself from the sibling anon_patch_finance_tx_id.

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 clarifies which request-body mode to use (ticketTypes preferred; legacy ticketPrice+ticketCount kept only for compatibility), which is genuinely useful selection guidance. However, it offers no when-to-use framing relative to the many finance siblings (get_finance, post_finance, patch_finance_tx_id), so usage is implied rather than stated.

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