Diagnose Presentation

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

Beyond the readOnlyHint annotation, the description adds substantial behavioral detail: 'WITHOUT mutating anything' assures non-destructiveness; 'Output is PASTE-SAFE by default: no absolute paths...' explains a key default and its security benefit; 'verbose=True adds the sandbox roots, engine locations, and full file path' describes what changes with verbose; and 'Reports the update-check state; the only place the check runs' reveals a unique side effect. All of this materially enriches the annotation-only signal.

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 dense but every sentence earns its place. It front-loads the core function, then successively adds parameter details, safety properties, usage guidance, and a clear sibling contrast. No filler or repetition; the structure with 'With file_path:' and 'verbose=True' cleanly maps to the two parameters.

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 has an output schema (so return structure need not be described) and annotations cover read-only behavior, the description completes the picture: it covers purpose, both parameters, non-mutation, paste-safety, verbose effects, and the update-check side effect. It even tells the agent the one scenario where this tool is the designated first step and where a different tool is needed. There is no obvious missing information an agent would need to invoke it 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?

With 0% schema description coverage, the description must carry full parameter meaning, and it does. For file_path it specifies the exact checks performed: 'existence, size, PowerPoint lock state, whether the package opens, and slide count.' For verbose it explains the added output ('sandbox roots, engine locations, and full file path'). This goes far beyond the bare schema names and defaults.

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 begins with a specific verb and resource: 'Self-check for this environment and, optionally, one file.' It enumerates concrete diagnostic outputs (engine availability, sandbox state, KS4P mode/policy, pack surface with token costs) and explicitly contrasts itself with the validate tool, which performs the real opens-clean check in PowerPoint. This clearly distinguishes it from sibling tools like get_presentation_info and get_presentation_view.

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 gives explicit when-to-use instruction: 'Run it first when any tool refuses unexpectedly or an export engine seems missing.' It also names the alternative and its limitation: 'The validate tool (assembly-export pack) does the real opens-clean check in PowerPoint,' telling the agent when not to rely on this tool for that purpose. This is exactly the kind of routing guidance agents need.

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