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

Adds context beyond annotations: the owner:va authorization requirement and the important side effect that 'Saved verification stays in Account until the owner removes it.' This clarifies what destruction actually means in this domain, though it doesn't explicitly say the connection can be re-established via start_va_connection.

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-loads the action and scope, then layers prerequisites, side effects, and exclusions in short clauses. Every sentence earns its place without redundancy.

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?

Given no parameters, no output schema, and annotations covering safety/idempotency, the description supplies what annotations cannot: required role and what is preserved after disconnect. A note on whether the disconnect is reversible would make it fully complete.

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?

The tool has zero parameters, so there is no parameter semantics to explain. A baseline of 4 is appropriate; the description correctly avoids inventing parameter details.

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 (stop this assistant's access to this account's shared VA facts), which implicitly distinguishes it from get_va_connection and start_va_connection. The scope — this assistant, this account — prevents ambiguity with other connection operations.

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?

Includes a prerequisite ('Requires owner:va') and explicit exclusions ('Does not disconnect another account or assistant, submit a claim or change VA records'), which narrow usage. 'When requested' is slightly vague about who requests it, keeping it from a 5.

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