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

Annotations only establish that this is a non-read-only, non-destructive, non-idempotent, closed-world write; the description adds genuinely non-obvious behavior: nothing is sent ('Sends no email'), the update is partial ('only the settings passed'), untouched values stay as-is, and there is a scoping rule for the template versus individual variants. Permission and default-scope facts are disclosed that 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?

It is short and front-loads the action, but the writing is telegraphic to the point of being hard to parse: 'only the settings passed, on the template, whose settings new variants copy, and on the variants' is a fragment whose referents must be reconstructed. Every sentence carries information, but the structure (stacked colons and verbless clauses) costs readability.

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 mutation with nested body objects, ~40 enumerated failure codes in the schema, and no output schema, the description covers scope, defaults, permissions, and side effects well. The remaining gap is the response shape — with no output schema, an agent gets no hint about what a successful call returns.

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?

Though top-level coverage reads as 33%, the schema itself documents each body field exhaustively; the description's added value is the partial-patch semantic ('only the settings passed') and the default scope of variantIds (template plus every editable variant) implied by 'on the template ... and on the variants'. It does not clarify the idempotencyKey or the params.id argument beyond what the schema already says.

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 — it 'changes how the variants' own emails are sent' — and anchors it to the app's Burst Emailing tab, so an agent can recognize the mutation being performed. It distinguishes itself from the closest sibling by name (updateBurstVariantRecipients handles recipients), though it never contrasts with updateBurstEmailConfig, the other email-settings writer, leaving some sibling ambiguity.

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?

The description explicitly routes the agent elsewhere for related but distinct concerns: recipients go to updateBurstVariantRecipients and reading a report's settings goes to getReportEmailConfig. It also gives a permission rule ('Members who only contribute change their own variants') that determines whether the call can be used at all. What's missing is an explicit statement of when to prefer this over updateBurstEmailConfig versus updateReportEmailConfig.

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