Assign a JSM alert to a person

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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true), and the description goes well beyond them: it discloses that the call is asynchronous, mandates verification via jsm_get_request_status with the returned requestId, and maps the common failure mode (HTTP 422 / failed status) to its cause. That is exactly the added behavioral context the annotations cannot carry.

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-loads the core purpose and the sibling distinction, then layers args, return shape, async caveat, example, and error mapping in a scannable order. Some content (the account id format and the 'not an email' warning) is repeated from the schema, which is the only thing keeping it from a 5.

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?

Despite an output schema existing, the description still surfaces the return shape and — more importantly — the asynchronous requirement to poll jsm_get_request_status, which an agent would otherwise miss. Combined with the error mapping and id-source guidance, nothing needed to invoke this correctly is absent.

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 compensates for the ambiguity traps: it stresses full alert id vs tinyId, and account_id as an Atlassian id rather than email/display name, plus how to obtain one from jsm_get_on_call or jsm_get_alert. This largely duplicates the schema text, however, so it is useful reinforcement rather than net-new semantics.

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 ('Make one person the owner of a JSM alert') and immediately contrasts it with the nearest sibling, jsm_add_alert_responder, by explaining that assignment confers ownership while adding a responder does not. An agent can select between the two without opening either 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 explicit when-to-use ('when triage has decided whose problem it is'), an explicit scope exclusion ('for that one alert rather than a class of them — routing rules, not assignment, are how a class of alerts finds its team'), and a prerequisite workflow example for the common on-call case. This is close to the ideal for routing guidance.

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