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

Annotations already flag destructiveHint=true and non-idempotency, but the description goes further and states exactly what is lost: changing a body field rebuilds the body from plain fields and discards block edits made in the editor, while subject/preheader/audience edits preserve the body. That is precisely the kind of "what gets destroyed" context the annotations cannot convey. It omits return/validation behavior, keeping it below 5.

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 sentences, front-loaded with the changeable state and fields, then the destructive body-rebuild warning, then the document override. Dense but each sentence carries distinct information. Slightly baroque in phrasing but nothing is wasted.

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 an 18-parameter destructive mutation with no output schema, the description covers the highest-risk behavior (body rebuild vs. preservation) that an agent needs before calling. It does not address partial-update semantics for the many optional fields or any confirmation requirements, leaving a small gap.

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 high (89%), so a baseline of 3 applies, but the description adds real meaning: it explains the side-effect difference between body-field edits and subject/preheader/audience edits, and that `document` replaces the whole email document exactly as get_newsletter returns it. That interpretation guidance is not derivable from the schema alone.

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?

The description names a specific verb (changes/updates) and resource (a draft or ready newsletter), and enumerates the fields it can touch, so it is clearly distinct from create_newsletter, get_newsletter or schedule_newsletter. It stops short of explicitly naming siblings to route against, so it lands just under a 5.

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?

Usage is implied rather than stated: the description assumes the agent already knows to reach for this when editing an existing newsletter, and never says when NOT to use it (e.g., create, generate, or schedule_newsletter for those intents). It does clarify the accepted states (draft or ready), which is useful but not a when-to-use rule.

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