Delete an RSS subscription

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

The annotation already marks destructiveHint as true, so the description's job is to add nuance. It does exactly that by specifying the precise behavioral nuance: 'Links that were already created from it stay where they are — only the subscription goes away.' This informs the agent of the non-destructive consequence on related links, which goes beyond the annotation's flat destructive flag.

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?

The description is a single, effective sentence that front-loads the action ('Stops polling a feed') and then adds a clarifying nuance. No unnecessary words or repetitions.

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?

Given that the tool has only two parameters, an annotation for destructiveness, and no output schema, the description covers the essentially needed behavioral uniqueness (keeping existing links). It is complete enough for an agent to understand the tool's effect without missing critical context, though it could marginally benefit from mentioning the two-phase confirmation process implied by the confirm_token parameter.

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?

The input schema describes both parameters with adequate descriptions (100% coverage). The description does not add additional parameter semantics beyond what the schema provides (e.g., no extra guidance on the confirm_token's two-step flow). Therefore, the score is at the baseline of 3 since the schema already carries the burden.

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 clearly states what the tool does: it stops polling a feed (delete operation on an RSS subscription). This is distinct from sibling tools like 'create_rss_subscription' and 'list_rss_subscriptions'. However, the verb 'stops polling' is slightly less direct than 'delete', but the context makes it clear.

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?

The description implicitly clarifies that existing created links are not affected, which helps an agent understand the non-destructive side effect. However, it does not explicitly state when to use this versus other tools (e.g., no mention of alternative approaches like disabling the subscription via another tool if that existed), nor does it mention prerequisites such as listing subscriptions first to get the ID.

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