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

No annotations are provided, so the description carries the full behavioral burden. 'Free' and 'The come-back-often primitive' hint at cost and polling cadence, but it never says how the `contact` value is used for notification, whether subscribing twice is idempotent, how webhook delivery interacts with polling, or what confirmation is returned. For a six-parameter mutation with zero annotation coverage, these are significant omissions.

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?

Very short and front-loads the core action, which is good. But two of its four sentences ('Free.' and 'The come-back-often primitive.') are marketing fragments with little operational value, and the space saved was not spent on the undocumented parameters.

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 annotations, no output schema, and 0% schema description coverage across six parameters, the description should explain the contact/notification mechanism and the target-selector rules. It explains neither, so an agent can form the call but not understand its consequences.

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 for six undocumented parameters. It restates the `event` enum (already in the schema) and implies the skill/category/instrument targets, but the required `contact` parameter is never explained, the `webhook` parameter is unmentioned, and the mutual exclusivity of skill/category/instrument is left to inference.

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 ('Watch a skill, category or instrument for an event') and enumerates the three event types, so an agent knows exactly what the tool does. It also names get_subscription as the companion read, distinguishing it from a plain fetch. The title ('Tell me when… (the retention hook)') adds nothing, so clarity comes entirely from the description.

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?

Explicitly tells the agent to 'Poll get_subscription for current matches,' naming the alternative and the workflow that follows subscription. It lacks explicit when-not-to-use guidance (e.g., use a webhook instead of polling when a URL is given) but the usage path is clear.

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