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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false), the description discloses the key non-obvious behavior: this is a background task taking one to several minutes that returns a jobId rather than the deck. It also names the fields returned on completion (id, embedUrl, openPath, presentUrl, editUrl), which compensates for the absent output schema. It stops short of stating whether the job can fail, whether it consumes credits, or what happens if polling is abandoned.

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 sentences, front-loaded with the core action and deliverables, then the async polling contract, then the disambiguation to create_presentation. Every clause carries information an agent needs (deliverable types, latency, return fields, alternative) and nothing is redundant.

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 7-parameter generation tool with no output schema, the description covers the gaps that matter: it explains the async jobId contract, the polling loop, the payload returned on completion, and the sibling alternative. An agent has everything required to invoke the tool and finish the workflow correctly.

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 the schema already documents goal, brief, theme, title, slides, audience and language with defaults and limits. The description adds only the framing that generation is driven 'depuis un brief', without clarifying how goal versus brief interact or how slides counts include the cover beyond what the schema says. Baseline 3 is appropriate when the schema carries the parameter burden.

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 uses a specific verb+resource ('Faire rédiger une présentation entière') and immediately enumerates the deliverables: outline, laid-out slides with diagrams/tables/figures, speaker notes, and credited royalty-free photos. It closes by naming the sibling to avoid ('Pour une présentation que vous rédigez vous-même, préférez create_presentation'), so an agent can distinguish it from create_presentation without inspecting either schema.

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 explicitly when to use this tool (full authoring from a brief) and when not to, naming create_presentation as the alternative for self-written decks. It also prescribes the follow-up flow: call presentation_job repeatedly until status is 'done', which removes any ambiguity about the next step.

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