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

Goes beyond the annotations (readOnly=false, openWorld=true, idempotent=false) by disclosing the subject prefix, that mail goes through the business's own email service, that links are untracked and content unnumbered, and that it costs nothing. It doesn't cover delivery failure behavior or whether repeated calls re-send, which matters given idempotentHint=false.

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?

One dense, front-loaded sentence with no boilerplate. "Links are not counted and nothing is numbered" is terse to the point of being slightly ambiguous, but every clause carries 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?

No output schema and only two parameters, so the description covers most of what an agent needs: recipient limits, subject behavior, sending infrastructure, and cost. It leaves the return value and any per-send limits unstated, a minor gap for an open-world mail action.

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 50% — only issue_id is documented there. The description compensates by explaining the `to` parameter (up to 5 addresses, typically the owner or a colleague), adding real meaning beyond maxItems=5. It adds nothing for issue_id beyond the schema's own reference to newsletters_write_issue.

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 states a specific verb and resource (email an issue as subscribers will see it) and pins down the test scope via the "[Test]" subject prefix and the 5-address cap, which separates it in spirit from newsletters_send_issue. It stops short of naming the real-send sibling, so an agent must infer that relationship from the name alone.

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 context is clear — this is a preview to yourself/colleagues ("the owner, a colleague") rather than a live send. No explicit exclusion like "do not use to deliver to subscribers; use newsletters_send_issue" is given, so the when-not-to-use case is left implicit.

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