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

With no annotations, the description carries the full burden and does real work: it discloses the output format and destination, that the draft is private until publish_page, that it draws on the brand kit, and that it spends one draft allowance (a quota/cost signal). It omits permission requirements, overwrite behavior on title collision, and failure modes, so it falls short of fully transparent.

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 action is front-loaded and each sentence adds distinct information (output, brand grounding, image inputs, privacy/quota). Minor looseness in clauses like 'where the customer previews it' keeps it from being maximally tight.

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 mutation tool with no annotations and no output schema, the description covers output, privacy, quota, brand grounding, and image inputs, but leaves several parameters (offer, tone, cta_url, cta_text, audience) with no meaning anywhere and does not explain what 'starts from a brief' means relative to the title/goal fields.

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%: goal, notes, title, images, and sections are documented in the schema, while tone, offer, cta_url, cta_text, and audience are undocumented in both places. The description reinforces the images parameter's provenance ('/m/... addresses from generate_image') and the notion of a brief, but does not compensate for the unexplained CTA and audience 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?

Specific verb (write) and resource (a complete, responsive landing page as HTML) with the destination (Documents) and the previewing party named. An agent can distinguish this from content-producing siblings like write_email_template or draft_pitch solely from the description.

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?

Conditional guidance is present: 'Grounded in the brand kit when one exists' and 'Pass the addresses of pictures you generated so the page uses them' tell the agent when certain inputs apply. It also routes the publish step to the sibling publish_page. However it does not state when this tool is preferred over other authoring tools or what preconditions must hold to call it.

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