cleanup_presentation

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states that the tool deletes in-memory state and on-disk scratch dir, which clearly communicates the destructive scope and implies non-destruction of the presentation itself. However, it does not mention idempotency, error behavior, or whether the presentation becomes unusable after cleanup, leaving some uncertainty.

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 a single, front-loaded sentence with no wasted words. It efficiently conveys the operation and its targets, making it both brief and clear.

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 that an output schema exists, return values are likely covered. The description provides the core operation but lacks usage guidance, edge-case behavior, and prerequisites. For a one-parameter cleanup tool, this is minimally viable but not comprehensive, especially considering the lack of annotations.

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?

The schema has no descriptions for presentation_id (0% coverage). The description references 'a presentation' but does not explicitly explain the parameter's meaning beyond the parameter name itself. It does not clarify the format, required context, or relationship to other objects. The description adds minimal value in compensating for the missing schema descriptions.

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 identifies a specific verb ('Delete') and a precise resource ('presentation's in-memory state and on-disk scratch dir'). This clearly distinguishes it from sibling tools like create_presentation, get_presentation, or delete_slide, which operate on the presentation or slides themselves. The scope of deletion is explicit, leaving no ambiguity about what this tool does.

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 provides no guidance on when to use this tool versus alternatives. It does not mention typical workflow positions (e.g., after render_slides_as_pngs or export_presentation_source), nor does it note any exclusions or sibling tools that might be more appropriate for similar tasks. The intended usage is only implicit in the name 'cleanup'.

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