gateway_notification_topic_update

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

Annotations contain only a title, so the description carries the full burden. It does add useful context: the affected subject ('current employee') and the auth requirement ('notifications:read'). But it omits significant behavioral traits: the tool can both subscribe and unsubscribe via the 'subscribed' parameter, and there is no mention of side effects, idempotency, or return 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?

Two sentences, both informative, with the core action front-loaded and the permission note second. It is appropriately short, though the brevity comes at the cost of missing content rather than trimming fat.

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 behavioral annotations, 0% parameter coverage, and one required parameter, the description leaves too much to inference: what topic_key values are valid, how topic_type affects behavior, and the unsubscribe path. The presence of an output schema covers return values, but invocation semantics remain under-specified.

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 0%, so the description must compensate, but it adds nothing about topic_key, topic_type, or subscribed. The word 'project' loosely echoes the topic_type default, but the required topic_key is entirely unexplained and the boolean subscribed parameter's semantics are not described.

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 clear verb and resource: 'Subscribe the current employee to project notifications.' It distinguishes the action from notification siblings like publish, list, get, and ack by naming the subscribe behavior. However, it does not explicitly name or contrast any sibling, and the tool name says 'update' while the description says 'subscribe', which is a minor mismatch.

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?

Only a permission prerequisite ('Requires notifications:read') is given. There is no guidance on when to use this tool versus alternatives like gateway_notification_publish or gateway_notifications_list, no when-not-to-use conditions, and no mention that setting subscribed=false covers unsubscribing.

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