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

Annotations only declare destructiveHint=true; the description adds real value by stating it affects EVERY live link at once (blast radius), that it returns a count of previously live links, and that it is preview-only until confirm is true. It stops short of saying whether revoked links can be restored or what happens to already-used/expired links, which is the main remaining gap for a destructive operation.

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?

Three short sentences: action and scope first, return value second, safety mechanics last. No redundant restatement of the tool name and no filler.

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 simple destructive tool with no output schema, the description covers what it does, what it affects, what it returns, and how to safely execute it. Missing only edge-case behavior (irreversibility, treatment of expired links) that would fully round it out.

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 only 33% — only confirm is documented in the schema. The description says nothing about planId or planType (WORKOUT vs DIET), so it doesn't compensate for the low coverage. The enum values are self-explanatory, but the description adds no semantic detail beyond the confirm gate already described in the schema.

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 every live private link for a plan" gives a specific verb (turn off) plus resource (share links) and scope (all live links for one plan). It clearly separates itself from siblings like create_plan_share_link, get_plan_share_info, and revoke_client_portal_links, which target different link types.

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 makes the bulk-revoke use case explicit and explains the confirm-gated preview behavior, so the agent knows how to invoke it safely. It doesn't name alternatives (e.g. get_plan_share_info to inspect links first, or revoke_client_portal_links for the other link type), so the routing picture is slightly incomplete.

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