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

Annotations already flag destructive, idempotent, and openWorld behavior. The description adds non-obvious mutation semantics: only passed fields change, empty strings clear specific fields, and a sole body cannot be cleared.

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?

Two compact sentences, front-loaded with [write] and the draft restriction; clearing semantics follow efficiently. Every sentence adds useful information with 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?

Annotations cover the safety profile, but with 10 completely undocumented parameters and no output schema, the description should do more to explain account identifiers, title, subject, and expected outcome. It covers the core mutation behavior but not enough to resolve every parameter.

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 0%, so the description must compensate. It documents some parameters (id/uuid, HTML body, text body, schedule, link label) but leaves email_account_id, email_account_uuid, title, and subject unexplained.

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 ('Changes') and resource ('DRAFT campaign'), and identifies the id/uuid options. The draft-only constraint clearly distinguishes it from editing a live campaign.

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 says it works on DRAFT campaigns and that a started campaign cannot be edited, which tells the agent when not to use it. It does not name sibling alternatives like save_email_draft, but the context is clear.

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