Unsubscribe from events

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is largely covered; the description adds that recording stops and the buffer is discarded, which is real behavioral context. It does not say whether buffered events are recoverable, whether the subscription can be re-established with the same id, or how an unknown/expired subscription_id is handled. The word "discard" sits in mild tension with destructiveHint=false, though a transient buffer is plausibly not what that hint covers.

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?

One short sentence, front-loaded with the verb and free of filler. It is arguably too terse for a tool that discards data, but nothing in it is wasted.

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 single-parameter lifecycle tool with no output schema and no parameter documentation, the description should at least identify the subscription identifier and the irreversibility of the buffer discard. As written, an agent knows the gist but not the prerequisites or the failure modes.

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?

There is only one parameter and the schema coverage is 0%, so the description must carry the burden; it does not. It never mentions subscription_id, where to obtain it, or what makes an id valid. Given a single trivial string parameter and a clear resource reference ("a subscription's"), this is a gap but a small one.

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 names a specific action pair ("stop recording", "discard") against a specific resource ("a subscription's buffer"), so an agent can tell this is the teardown counterpart to a subscription. It never names the sibling it pairs with (e.g. subscribe_events), so the differentiation is implied rather than stated.

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?

There is no explicit when-to-use guidance: nothing says this should be called after finishing with a subscription, nor what happens if it is called without a prior subscribe. The pairing with subscribe_events must be inferred entirely from the name.

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