preview_pagesReturns pictures of the spreads the book prints, laid out by the same code that makes the printer’s file: a page by its number, a person’s first page, or the first message when neither is given.
| Name | Required | Description | Default |
|---|---|---|---|
| book | Yes | The book’s handle. | |
| pages | No | Page numbers, up to four. Each picture is the spread the page is on. | |
| person | No | A name as it prints, for that person’s first page. |
Changes observed during successful MCP inspections.
Input schema / properties / book / descriptionPrevious value: -"The handle start_book gave you."New value: +"The book’s handle."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds real value beyond them: the output is a print-faithful preview generated by the printer's own layout code, and the no-argument case yields the first message. It omits any note on image count, size, or delivery format.
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?
A single front-loaded sentence with the main verb first and a colon-separated enumeration of selection modes; no filler. Slightly dense prose but every clause carries information.
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?
With no output schema and a tool whose return value is images, the description never says what the pictures arrive as (URLs, embedded data, count per call) or whether the four-page cap in the schema is enforced server-side. Adequate for correct invocation, but incomplete for interpreting results.
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 coverage is 100%, so baseline is 3. The description nevertheless contributes new meaning the schema lacks: the precedence rules among pages, person, and the default first-message behavior, plus confirmation that each page yields its containing spread.
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 names a specific verb and resource ('Returns pictures of the spreads the book prints') and adds a strong qualifier: the rendering comes from the same code that builds the printer's file. That distinguishes it from any sibling (order, send_it_out, book_status) without ambiguity.
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 spells out the three selection modes and, crucially, the fallback ('the first message when neither is given'), which tells the agent it can call with only the required book parameter. It does not explicitly say when to prefer this over reviewing an order or status, so it falls short of a full when/when-not statement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.