add_mailbox

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

With no annotations, the description carries the full burden and does well: it discloses the precondition (SMTP and IMAP login are tested first), the conditional write ('saves only when both pass'), and provider-specific auth requirements. It omits failure/error behavior details and any auth requirements for the calling client itself.

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 short sentences, front-loaded with the action and followed by the two provider caveats; every sentence earns its place. Minor deduction for the missing punctuation in the opening sentence ('Connect a mailbox Tests SMTP...'), which creates a run-on.

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 tool with a two-branch oneOf schema and no output schema, the description covers the key selection-relevant facts (provider auth differences, validation-before-save) but says nothing about what a successful connection returns or how validation failures surface to the caller.

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 effectively high and the oneOf variants fully enumerate required fields per provider, so the schema does the heavy lifting. The description only adds meaning for the Google password case (app password), matching the baseline of 3.

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+resource ('Connect a mailbox') and adds the save semantics, so an agent knows this persists a mailbox rather than merely testing credentials. It reads clearly against the sibling list_mailboxes, though no sibling is named explicitly.

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?

Provides concrete routing context: Google requires an app password, and Microsoft 365 must be connected via OAuth from the dashboard, which strongly implies this tool is not the path for M365. It stops short of naming an alternative tool or stating exclusions outright.

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