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

Annotations already indicate destructiveHint=true, meaning the tool may have side effects. The description adds context about the sensitive-tier and approval requirements, which is valuable behavioral insight. It clarifies that the tool creates a throwaway artifact, not persisted content, and mentions the rendering context (in the well). This goes beyond the annotations and helps the agent understand the side-effect profile and approval flow.

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 description is relatively concise and front-loaded with the purpose and scope. It includes a routing section and a note on sensitive-tier approvals, which adds useful context without being verbose. However, the sensitive-tier note is somewhat dense and might be more effective if broken up, but overall it's efficient for the information conveyed.

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?

Given the tool's complexity (3 params, no output schema), the description covers the essential aspects: what it does, what it doesn't do, when to use it, and the approval workflow. The annotations already provide safety hints, so the description doesn't need to reiterate that. The description is complete enough for an agent to know when and how to invoke it correctly, though it could benefit from a note on the return value (though no output schema exists).

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 100%, so all three parameters (title, prompt, companyId) are documented in the input schema. The description doesn't add much beyond the schema because it doesn't elaborate on parameter syntax or provide examples beyond what's in the schema. The schema itself is sufficiently descriptive, so the description's minimal addition is acceptable; baseline 3 is appropriate.

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 clearly states the tool's purpose: generating a small, self-contained HTML visual (comparison table, diagram, list, mini-dashboard) as a throwaway artifact for the operator's screen. It distinguishes from persisted content by explicitly noting it's not a webpage and renders once. However, it doesn't explicitly differentiate from sibling tools like generate_carousel, generate_vector_image, or generate_video, which likely have overlapping purposes of generating visuals.

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?

The description provides explicit routing guidance: use this for quick throwaway visuals for the current conversation, but not for webpages or persisted content. It also includes the sensitive-tier approval flow, instructing the agent to call it on the first clear ask and not re-ask once approval is given. This is clear and actionable.

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