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

Goes well past the annotations (destructiveHint=true, idempotentHint=false) by explaining *what* is destroyed: `blocks` replaces the body wholesale, so the agent must round-trip the full saved block list rather than patch one block. It also discloses execution semantics — 'it runs at once, as the person' — and the workspace precondition, which no annotation conveys.

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?

Front-loads the scope and the mutable field list, then the body-replacement rule, then the trailing constraints. Dense but nearly every clause carries operational meaning; the final two one-liners (workspace precondition, execution timing) could have been folded into the opening for tighter structure.

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 12-parameter mutation with a deeply nested `blocks` union, the description supplies the one thing the schema cannot — the interaction between `blocks`, `brief` and `productIds` (replace vs regenerate) — plus auth/scope and preview routing. An output schema exists, so return values need no explanation.

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 adds real semantics the schema can't: `subjectB: null` stops the A/B test, `brief` or `productIds` regenerates the body instead of editing fields, and every other field 'changes only itself.' The read-modify-write contract for `blocks` is the single most valuable clarification here.

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?

Opens with a specific verb and resource plus a hard scope boundary — 'a campaign that has not gone out (a draft or a scheduled one)' — then enumerates exactly which fields can change. This separates it cleanly from draftCampaign (creation), scheduleCampaign, deleteCampaign and sendTestCampaign without the agent needing to open any 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?

Routes the agent through the workflow: readCampaign to fetch blocks as saved, readCampaigns to obtain the broadcastId, sendTestCampaign to see the result in an inbox, draftCampaign as the analogue for brief-driven body rewrites. It also states the precondition 'Only for a workspace with subscribed email contacts.' It stops short of explicitly naming what to do with an already-sent campaign (resendCampaign), which keeps it off a 5.

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