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

Annotations carry no behavioral hints at all, so the description does real work here: it discloses idempotent upsert semantics ("repeated calls update one alert"), the absence of notification side effects, and the admin permission requirement. It stops short of saying what happens on invalid input or whether the alert persists/expires.

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?

Three short sentences, front-loaded with the core action, and every clause carries information (idempotency, no notification, permissions). No filler.

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 and no annotations, the description should say what a raise returns (alert id? the existing alert?) and what the group parameter means for shared visibility. It covers the mutation semantics but leaves the response contract and one parameter unexplained.

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?

Coverage is 60%: key, url, and detail are described in-schema, while title and group have empty descriptions. The description reinforces the key semantics but adds nothing about group (the field that determines the "shared" scope) or title formatting, so it doesn't compensate for the 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?

"Record or update a condition under a stable key" gives a specific verb pair and resource, and "No notification is sent" separates it from notify_send/sms_send. However, the sibling alerts_update exists and the description never distinguishes an upsert-by-key from that dedicated update tool, so sibling differentiation is incomplete.

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?

"Group administrators may raise shared alerts" supplies a permission precondition, and the upsert-by-key hint implies repeated calls are safe. But there is no explicit when-to-use/when-not guidance versus alerts_update or alerts_list, leaving the main selection question unanswered.

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