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

Annotations already declare destructiveHint=true, so the bar is lower, yet the description adds real value by specifying exactly what is destroyed (the stored keychain password) and what survives (Bridge install and mailbox). It stops short of saying whether reconnecting requires re-entering the password or whether the deletion is reversible, which would have completed the picture 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 tight sentences with zero filler: the destruction scope is front-loaded, then the exclusion, then the parameter rule. Every sentence carries distinct information an agent needs.

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?

With rich annotations (destructiveHint, openWorldHint=false), full schema coverage, and an output schema, the description covers the remaining burden: what is removed, what is untouched, and how to supply the account. Nothing material for correct invocation is missing.

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 description coverage is 100%, so both parameters are already documented; the description's account guidance largely restates the schema's own 'Required when more than one account is connected' text. It adds a useful pointer to proton_status as the source of the address but says nothing about `confirm`, which the schema itself flags 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 ('Disconnects one Proton Mail account') and immediately bounds the scope: it removes the Bridge password from the macOS keychain, not the Bridge or mailbox. This is clearly distinguishable from sibling disconnects (thunderbird_disconnect, gdrive_disconnect) by naming the exact artifact removed.

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?

Explains when the tool applies and gives the concrete rule for identifying the account ('the address proton_status lists; with one account it can be omitted'). It does not name an explicit alternative or when-not-to-use case, but the scope caveat ('Bridge and mailbox are not touched') implicitly steers the agent away from expecting a full uninstall.

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