Publish an HTML-native presentation

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

Annotations declare the write profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), and the description adds real pipeline detail: sanitization, validation, persistence, access-control and CSP application, plus the returned viewer URL. It stops short of stating duplicate/re-publish behavior, but this is well above the annotation baseline.

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?

Purpose is front-loaded in the first sentence, and the procedural visual-QA guidance that follows is dense but task-relevant. The middle visual-QA paragraph is long and somewhat repetitive about re-rendering, costing a point, but every section carries operational weight.

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 write tool with no output schema, the description supplies the return value (viewer URL), the pre-step (get_recipe), the QA workflow, and the sanitization/access-control behavior. The nested sharing modes are left to the schema, which is acceptable at 75% coverage, but a brief note on the default private behavior would have completed it.

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 75%, so the schema already documents most parameters, including the nested sharing object. The description only alludes to parameters obliquely ('declared desktop canvas' implying aspectRatio, 'applies access controls' implying sharing) without adding syntax or constraints. 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?

States a specific verb (create/publish) and resource (HTML presentation deck), enumerating artifact types (slides, pitch deck, keynote) that make the target unambiguous. It does not explicitly contrast with siblings publish_html or publish_page, so it is clear but not sibling-differentiating.

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 a concrete required precondition (call get_recipe with recipeId "presentation-deck" first) and a conditional path for when rendering tools are unavailable. However, it never routes the agent among the actual sibling publish tools (publish_html, publish_page), so alternatives within the toolset remain unaddressed.

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