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

With no annotations, the description carries the full burden and does reasonably well: it discloses the cost ('Spends one draft allowance'), the persistence side effect (filed in Documents), and the grounding dependency on a brand kit. It omits permission/auth requirements and what happens if the draft allowance is exhausted, which keeps it from a 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 front-loaded sentences that each carry information: what is produced, how it is grounded, and where the result can go. No filler, though the clause about Outlook/Gmail rendering is parenthetical detail that could be trimmed.

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 11-parameter generative tool with no annotations and no output schema, the description covers the output artifact and cost but says almost nothing about the inputs, so the agent cannot tell what a good 'brief' looks like or how sections/cta fields map to the rendered email. Adequate minimum viability, but with a clear parameter-semantics 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 description coverage is only 18% (just title and images), and the description does not compensate by explaining the other nine parameters (goal, tone, notes, offer, audience, sections, cta_url, cta_text, preheader). 'From a brief' is the only hint at how the inputs are consumed, leaving the agent to infer the meaning and format of most fields.

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+resource (write an HTML marketing email) and specifies the technical rendering approach (tables and inline styles for Outlook/Gmail) plus the side effect (filed in Documents for preview). It is clearly distinguishable from siblings like write_landing_page and create_email_draft, which is explicitly framed as a downstream destination rather than the same action.

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?

It states the grounding condition ('when a brand kit exists') and routes the agent to the correct downstream tools, noting that create_email_draft and app actions 'ask first'. It never states when NOT to use this tool (e.g., plain-text or non-marketing emails), so it stops short of full when/when-not coverage.

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