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

With no annotations, the description carries the behavioral burden and does well: it discloses credit cost (1 credit, 2 with image_url), that the AI actually looks at the slide when image_url is supplied, that output is not persisted, and the required follow-up action. It does not cover authorization or rate limits, but for a generation tool this is solid disclosure.

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 front-loaded and efficient: it first states what the tool does, then the cost model, then the critical persistence caveat and required next step. Every clause earns its place.

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?

The description covers the most important workflow facts—cost, optional image handling, non-persistence, and the required follow-up tool—but with 7 parameters, 43% schema coverage, no annotations, and no output schema, it omits enough parameter-level context that an agent may still need to inspect the schema carefully.

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 only 43%, so the description needs to compensate for several undocumented parameters. It adds useful meaning for image_url via the credit cost and AI-vision behavior, but says nothing about slide_number, total_slides, extracted_text, next_slide_text, or previous_script, leaving most parameter semantics to an incomplete schema.

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 states a specific verb and resource: 'AI-write what the presenter says on one slide.' It also scopes the output by the presentation's language and distinguishes this per-slide script generation from broader sibling tools such as generate_agent_script or generate_transition_phrases.

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 clearly explains the workflow after generation: the result is 'NOT saved' and must be placed 'into narrator_script with set_presentation_slides.' This gives strong operational context, though it does not explicitly compare when to use this versus other script-generation siblings.

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