Check an email

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

Annotations already declare readOnlyHint and openWorldHint, and the description reinforces the safety profile with 'Read-only; sends nothing.' More valuably, it discloses network behavior that the annotation alone does not: check_links_live uses HEAD requests only and never requests unsubscribe or click-tracking links. It does not describe what a failed check looks like or how results are returned.

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?

The core purpose and checklist are front-loaded in the first sentence and the input-mode and safety notes follow. The middle clause is a long parenthetical list that is dense but scannable, and no sentence is 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?

For a 10-parameter tool with no output schema, the description covers inputs and behavioral limits well but says nothing about what the check returns or how findings are structured. An agent knows how to call it but not what to expect back, leaving a meaningful 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?

With 70% schema coverage across 10 parameters, the description adds real meaning: it explains that personas are rendered to test personalization ('several synthetic personas'), that link checks cover non-production hosts, unsubscribe, UTMs and approved domains, and that transactional mail skips the unsubscribe rule. A few parameters (name, subject, preheader) are only implied by the checklist rather than directly explained.

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 opens with a specific verb-and-resource ('QA one email before it sends') and enumerates exactly what is validated: HTML structure, Outlook conditionals, Gmail clipping, alt text, links, personalization, subject, sender, brand terms, spelling, footer text. It does not explicitly name sibling tools like check_message or check_campaign, so the agent must infer the distinction, keeping it below 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?

'QA one email before it sends' gives a clear usage context, and 'Pass HTML or a local file path' states the accepted input modes. It stops short of naming alternatives (e.g. check_campaign or check_message) or stating when not to use this tool, so there is no explicit routing guidance.

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