개입 요청 이슈 만들기

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

With no annotations, the description carries the full load and does well: it discloses that the issue lands in a private repo, that a representative is assigned, that an Apps Script mail is fired exactly once and its result returned, and it warns that mail.ok is not proof of inbox delivery. It omits permission/auth requirements and failure behavior, which keeps it short of a 5.

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?

Every sentence earns its place: purpose and assignment first, then body-content rules, then mail side effect, then the no-notify instruction, then the title prefix rule, then the mail.ok caveat. No filler and the most important constraint is front-loaded.

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 mutation tool with no annotations and no output schema, the description is unusually complete: it explains the created artifact, the automatic mail step, the returned mail result, and the mail.ok semantics. Only auth/permission preconditions and error handling are missing, which is a minor gap given the rest.

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 meaning beyond the schema: the body must avoid PII and secrets, must state situation/decision/options/status, and the title must begin with the AUTH:LLM(Modelname-thinkinglevel) prefix reflecting real model and reasoning level. These are usage constraints the schema only partially encodes.

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 (create an intervention-request issue in a private repo) plus the side effect of assigning the representative as assignee. It also explicitly distinguishes itself from the sibling wyea_notify by telling the agent not to chain that call.

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 conditional guidance: use this tool and do NOT additionally call wyea_notify, since the mail is already triggered once here. It also prescribes what belongs in the body. It does not, however, contrast itself with other siblings such as wyea_ask or wyea_check, so the when-to-use picture is only partly complete.

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