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

Annotations already declare destructiveHint=true and readOnlyHint=false; the description adds real value on top by scoping the destruction ('removes the password Local MCP stored') and explicitly listing what is untouched — Thunderbird's own saved password, the mail, and reading behavior. It does not mention reversibility or what reconnecting requires, which keeps it below a 5.

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 dense sentences, each load-bearing: the action, the non-effects, and the parameter rule. The core effect is front-loaded and nothing is repeated from the annotations or schema.

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?

An output schema exists, so return values need not be described. For a destructive, zero-required-parameter disconnect tool, the description covers the effect, the non-effects, and the parameter rule an agent needs to call it correctly.

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%, so the baseline is 3, but the description goes beyond the schema by spelling out the conditional requirement for `account` in prose and where to obtain valid values. It omits any note on the vestigial `confirm` parameter, though the schema already labels it as ignored.

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 ('Stops Local MCP from sending from one Thunderbird account') and immediately narrows the mechanism ('removes the password Local MCP stored for it from the macOS keychain'). This distinguishes it from a generic account-removal or Thunderbird-level sign-out, which matters given the many other *_disconnect siblings.

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?

Gives an explicit precondition for the `account` parameter ('with one connected account it can be omitted, with several it must be given') and points at thunderbird_accounts_status as the source of valid ids. It stops short of naming when to prefer disconnect over leaving an account configured, but the operational context is clear.

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