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 asynchronous job model, the returned jobId, and the follow-up polling tool. It also documents fidelity behavior (text kept word for word, tables/notes/images carried over) which an agent cannot infer from annotations or schema.

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?

Two sentences, front-loaded with the transformation result followed by the async contract; the parenthetical list of preserved content earns its space by defining fidelity guarantees. No filler or repetition of the tool name.

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 side-effecting import with no output schema, the description covers what is produced and how to retrieve results, which is the critical missing piece for async tools. It leaves open which of url/asset must be supplied and whether a new presentation is created or an existing one is targeted.

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 75%, so the schema already documents url (public https, 20 MB max), asset (/uploads/<id>) and theme (default 'ocean'). The description only reinforces the theme-to-layout relationship ('mise en page selon le modèle choisi') and says nothing about url/asset being alternatives, despite zero required parameters.

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 gives a specific verb and resource ('Importer un PowerPoint' / .pptx) and immediately specifies the outcome: one slide per slide, with text preserved verbatim plus tables, notes and images, laid out per the chosen template. This clearly distinguishes it from siblings such as create_presentation, generate_presentation or import_html_page.

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 tells the agent this is a background task returning a jobId and that presentation_job must be called to get the id and links once finished — an explicit routing instruction to a sibling tool. What's missing is when NOT to use it versus create_presentation/generate_presentation or whether url vs asset is the required input path.

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