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

Annotations only give the generic mutation profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true); the description goes far beyond by disclosing the 202/awaiting_approval response shape, the review_url, the mixed-request partial-apply semantics ('Applied now: ...'), the change_in_progress failure mode and what was/wasn't applied, and the 'approved' no-op case. This is unusually rich behavioral context for an agent.

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?

Long but dense with no filler; it is front-loaded with the parameters and their effects, then the outcome branches. Slightly heavy for a two-parameter tool, but each sentence carries distinct operational information.

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 no output schema and only generic annotations, the description supplies the response shapes, status values, and error handling an agent needs to act correctly. Nothing material is missing for invoking and interpreting this tool.

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 baseline is 3, but the description adds meaning the schema doesn't: max_sends_per_day applies account-wide across all campaigns, and auto_send_enabled=false stops ALL sending while true resumes it. That is genuine semantic enrichment beyond the field-level schema text.

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 (update the Gmail sending schedule) and enumerates the two controllable settings with their scope. An agent can distinguish this from read-only siblings like outreach_sending_status or outreach_get_campaign 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?

Explicitly covers when the change applies immediately (lowering the cap, disabling) versus when it needs user approval (raising, enabling), names the required user action (show the review_url), and warns to confirm with the user before changing these because they control real email volume. It also routes to list_proposals for the recurring case.

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