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

Annotations already declare destructiveHint=true, readOnlyHint=false, idempotentHint=false, so the safety profile is covered by structured data. The description contributes one genuinely extra behavioral fact – a Confirm button is shown first – but omits what revocation actually destroys (does the link URL die permanently? do existing submissions or reviews survive? is it reversible by re-creating a link?).

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 short sentences, front-loaded with the action, no filler or repetition of the title. The confirm-button note is tangential but short enough to earn its place as a UX fact.

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 an irreversible destructive mutation with an undocumented enum parameter and no output schema, the description is too thin: it does not say what is destroyed, what the result looks like, or how the two purpose values change behavior. Annotations supply the safety flag but not the operational detail an agent needs to call this safely.

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?

With 0% schema description coverage and a required enum parameter (purpose: status_view | data_intake), the description carries the whole burden and provides nothing. It never explains what business_id refers to beyond 'a business', and critically never says whether purpose selects which of two links is revoked or whether omitting it revokes all – a real risk of an unintended wide revoke.

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?

"Turn off a business's share link" names a specific verb (turn off/revoke) and resource (share link), which is enough to separate it from create_share_link, show_share_link, or list_share_links. It stops short of explicitly naming those siblings or stating scope (one link vs. all links), so it is clear but not fully differentiated.

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 gives no when-to-use or when-not-to-use guidance and does not point to alternatives: it never says how this differs from removing/replacing a link via create_share_link, nor what preconditions exist. Only an implied usage is conveyed by the verb itself.

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