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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds the crucial detail that nothing of the old value is retained, that an empty string clears the signature, and that Outlook mailboxes are unsupported. These are behavioral facts the annotations cannot express.

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 destructive replace action, then the prerequisite, then the provider restriction. No filler.

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 no explanation, and the description covers destruction semantics, prerequisites, and provider limitations. Nothing an agent needs to invoke this correctly 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 coverage is 100%, so both parameters are already documented (baseline 3). The description adds real semantic value by explaining the empty-string case for 'signature' and clarifying that the target is the mailbox's own send-as identity, though it does not elaborate on the HTML sanitisation noted in the schema.

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 precise verb+resource ('Replace the signature on the mailbox's own send-as identity'), which is clearly distinct from the read-side sibling settings_send_as_get. An agent can tell what this writes and to what object without opening the 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?

Gives an explicit prerequisite/alternative ('read it first with settings_send_as_get') and an explicit exclusion ('Gmail mailboxes only: an Outlook mailbox exposes no signature to write'). Both when-to-use and when-not-to-use are covered.

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