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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description's real contribution is scope-of-destruction: the disconnect takes effect on the app's next call, and whether it ends the app entirely or only for this business depends on ownership and allBusinesses status. That is genuinely non-obvious behavior no annotation conveys. It does not say whether the disconnect can be undone/reconnected or what error conditions look like.

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 the id source, then the conditional consequences, which is the right ordering. Slightly dense and the closing sentence ('Disconnecting yourself ends this connection') partially restates the 'ends altogether' condition, so it is not perfectly waste-free.

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 single-parameter destructive mutation with no output schema, the description covers the action, the id source, timing of effect, and the branching scope of destruction across ownership cases — exactly what an agent needs before calling. Remaining gaps (reversibility, errors) are secondary.

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?

There is one parameter at 0% schema description coverage, so the description must carry the load. It does add real meaning by telling the caller the id must come from list_connected_agents, but it says nothing about format, validity, or what happens with a stale/foreign id, so the compensation is partial.

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?

Uses a specific verb+resource pair ('Disconnect one AI app from this business') and immediately circumscribes the scope to a single entity. It also names the sibling that supplies the identifier (list_connected_agents), so an agent can tell it apart from the listing/connection siblings without opening a 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?

The description effectively routes the agent: get the id from list_connected_agents, then call this. It also frames the conditional outcome cases (sole-connection app, own app, another person's allBusinesses app, self), which implicitly tells the caller what situation they are in. It lacks an explicit 'do not use this if…' exclusion or a stated prerequisite such as ownership/permission.

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