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

Beyond the annotations (readOnly=false, destructive=false, idempotent=false) it discloses the things an agent actually needs: the call blocks until the page is ready, it returns the URL, the default visibility is private to the caller, sandbox restrictions on external resources, and the run-time capability model. It also clarifies that scripts cannot fetch anywhere and libraries must be version-pinned, which prevents a whole class of failed publications.

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?

Front-loads what the tool produces and the privacy default, then layers the interactive-page case and the alternative. Dense but every sentence carries information; some sentences are long and the state/capabilities discussion could be split for scannability, so not a 5.

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, nested-schema, capability-bearing creation tool with an output schema, the description covers the decision-relevant surface: default visibility, blocking-then-URL semantics, content sandbox rules, the state/capabilities model, and the sibling alternative. Return values are documented by the output schema, so leaving them to it is appropriate.

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 100%, so the schema already carries the heavy lifting and a 3 is the baseline; the description earns an increment by explaining the intent behind capabilities and state.rules (a page that must remember a checklist/poll/sign-up) and by stating 'Pass the whole document as content'. That usage-level framing adds meaning the property descriptions alone don't convey, though the per-field detail remains in the schema.

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?

Opens with a specific verb and resource ('Publish an HTML page or a Markdown document as a Bisque Artifact') and immediately defines the resulting object as a persistent, versioned page at a stable URL. It also names the sibling to use instead when the goal is a narrated deck (create_presentation), so an agent can discriminate it from neighbors without reading schemas.

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?

Gives clear positive usage context (whole document as content, update later with update_artifact, declare capabilities only for interactive pages) and one explicit alternative ('For a narrated presentation use create_presentation instead'). It stops short of full when-not guidance — e.g., it never says when to use share_artifact or create_artifact_thread instead of folding sharing into this call — but the routing it does provide is concrete.

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