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

Annotations already flag destructiveHint=true and idempotentHint=true; the description goes further by disclosing the non-obvious side effect (existing connections persist), the auth requirement (accounts.manage, held by Admin), and the return payload. This is context an agent cannot get from the structured fields.

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?

Four short sentences, front-loaded with the action and its immediate effect, then side effects, permissions, and return value in descending order of importance. 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 destructive mutation with no output-schema ambiguity, the description covers effect, collateral behavior, required permission, and the follow-up tool, leaving nothing an agent needs before calling.

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%, including which tool produces the token ('returned by create_connect_link'), so the description correctly leaves parameters to the schema. It adds no extra meaning of its own, which is the baseline case.

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 and resource ('Revoke a connect link') plus the immediate effect ('stops working at once'), which separates it from create_connect_link and from remove_account. The agent can identify what it does 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 scopes the behavior ('accounts already connected through it stay connected') and names the correct alternative ('remove them with remove_account'), so the common wrong-tool mistake is pre-empted. It also states the permission prerequisite.

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