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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds real substance beyond them: what survives the delete ('SmartPins the feed already generated are left alone'), which only future Pins stop, and the not-found failure mode with its implication (success means it really was removed). That's strong; the main omissions are auth/permission requirements and whether the removal is reversible or recoverable.

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?

Front-loaded with the action and its effect, then consequences, then the alternative, then the safety caveat — a sensible order of decreasing call-criticality. Every sentence carries distinct information; nothing repeats the schema or annotations verbatim.

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?

This is a destructive one-param tool with an output schema and full annotation coverage, and the description still covers effect scope, data preservation, error semantics, the temporary alternative, and a confirmation policy. Nothing an agent needs to call it safely is missing.

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 coverage is 100% and the schema already documents feedId's sources (list_feeds, connect_feed, get_feed), so the baseline is 3. The description earns above baseline by tying feedId to an organization-scoping failure ('Fails with a not-found error if the feed is not this organization's'), which the schema does not say.

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 ('Removes the subscription') plus the concrete consequence ('the daily check stops and no further Pins are generated'). It also distinguishes itself from update_feed (pause) and from cancel_generation in the sibling set, so an agent can route correctly without opening the schema.

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 names the trigger ('when the user wants Tailwind to stop watching a feed for good') and the alternative for the temporary case ('pause it with update_feed'). It goes further with a confirmation rule for feeds the user did not explicitly name, which is exactly the kind of operational guidance an agent needs.

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