preview_book

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

With no annotations, the description carries the full burden. It discloses the key behavioral trait: the operation is asynchronous ('Returns immediately') and instructs the agent on how to track completion. This is essential context for an agent to avoid blocking or misinterpreting the return. It does not cover failure modes or side effects, but the core behavior is well communicated.

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 that packs the essential facts: what it does (starts full preview), the outputs (PDF + EPUB), the async nature ('Returns immediately'), and how to get results (poll or wait). Every phrase earns its place; no filler or redundancy.

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 one-parameter async trigger with no output schema, the description covers the immediate interaction flow: initiate and then poll. It does not mention prerequisites (e.g., book must exist) or error handling, but given the sibling tools like check_book_exists and the simple parameter, this is reasonably complete. The main omission is the lack of slug explanation, but that is more a parameter-semantics issue.

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 input schema has one required parameter 'slug' with no description, and schema description coverage is 0%. The description does not explain what 'slug' refers to or its expected format, leaving the agent without guidance beyond the raw type 'string'. Since the description should compensate for the schema's lack of detail, this is a notable gap.

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 clearly states the verb 'Start' and resource 'a book', and specifies the scope as 'full preview generation' with formats 'PDF + EPUB'. This distinguishes it from siblings like preview_subset and preview_single, though it doesn't explicitly name them. The purpose is unambiguous and task-focused.

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 implies usage for full previews by specifying 'full preview generation', but it does not explicitly state when to choose this over preview_subset or preview_single. It does provide operational guidance on monitoring completion via get_job_status or wait_for_job, which is helpful but not a direct comparison with alternatives.

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