Skip to main content
Glama

Read an ebook

get_ebook
Read-onlyIdempotent

Read one of the caller's existing Unplain ebooks by id, including its current styling under theme.design (colours, fonts, type sizes, spacing, cover layout, and which preset it resembles) in the same field names update_ebook accepts. cta reports the CTA page (layout, headline, body, button, showButton, link, social links, credit) in the names update_ebook accepts, and ctaLayoutDrawn the layout it draws (what 'auto' picked). ctaButtonInPdf says whether the exported PDF draws the button, and ctaButtonWarning, when present, why a shown button will not be in it (no real url). mode: 'outline' (default) returns every block's id, type and a truncated preview, which is what update_ebook's operations address; 'metadata' returns settings only, and is the cheap way to inspect a design before changing it; 'full' returns complete block text. Tables, buttons and images are readable in both: outline gives each table's rowCount, columnCount and headers, each button's text and href, and each image's sizePreset and align; full adds the whole table (headers, rows, align, in the shape set_table accepts) and the image's alt. outline and full return at most 'limit' blocks (default 150, max 500) starting at 'fromBlockId'; when blocks remain the result carries nextBlockId, to pass back as fromBlockId, and blockCount is always the total. Read every page before replacing the body with update_ebook's content. A block may carry a 'treatment' (pullQuote, callout, steps, stat or statCaption): styling chosen automatically at import that renders it more prominently, such as a stat drawn at display size in the accent colour. ALWAYS call this before update_ebook: it returns the block ids to edit and the version that makes the update safe against a simultaneous edit in the web app. If you only know the ebook by name, call list_ebooks first to get its projectId.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "projectId": "<projectId>"
    },
    "name": "get_ebook"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNometadata: settings only, no content. outline: every block's id, type, any treatment, and truncated text (use this before editing). full: complete block text.outline
limitNooutline and full modes: most blocks to return (default 150, max 500). One more may be included so an image and its caption stay together. When blocks remain, the result carries nextBlockId.
projectIdYes
fromBlockIdNooutline and full modes: start the block list at this block (inclusive). Pass the nextBlockId a previous call returned to read the next page. Omit to start at the first block.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / fromBlockId
      Added value: +{
      +  "description": "outline and full modes: start the block list at this block (inclusive). Pass the nextBlockId a previous call returned to read the next page. Omit to start at the first block.",
      +  "maxLength": 64,
      +  "minLength": 1,
      +  "type": "string"
      +}
    • addedInput schema / properties / limit
      Added value: +{
      +  "description": "outline and full modes: most blocks to return (default 150, max 500). One more may be included so an image and its caption stay together. When blocks remain, the result carries nextBlockId.",
      +  "maximum": 500,
      +  "minimum": 1,
      +  "type": "integer"
      +}
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), but the description adds substantial behavioral context beyond them: truncation of block previews, a default limit of 150 with max 500, possible 'limit + 1' inclusion to keep an image with its caption, nextBlockId pagination, and always-present blockCount. It also explains the conditional ctaButtonWarning and the 'treatment' annotation semantics that annotate special rendering.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the verb, resource and headline return content, and nearly every clause carries usable information given there is no output schema. It loses a point for being a single dense wall of text with mild repetition ('in the same field names update_ebook accepts' appears twice in near-identical form).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read tool with no output schema and four parameters, the description covers modes, pagination contract, total counts, field-name compatibility with update_ebook, warning fields, and the mandatory pre-update check. An agent could call this correctly without opening any other documentation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75% (projectId is undocumented in schema), and the description compensates by explaining that projectId comes from list_ebooks when only a name is known. The mode parameter is fleshed out with what each mode actually contains (outline: ids/types/truncated preview; full: complete text plus whole tables and image alt), though limit and fromBlockId largely repeat the schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Read one of the caller's existing Unplain ebooks by id') and immediately scopes the return payload: styling under theme.design, cta fields, mode-dependent block content. It is clearly distinguishable from sibling tools such as list_ebooks (name→id lookup) and update_ebook (mutation), both of which are named.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use and when-to-use-something-else guidance: 'ALWAYS call this before update_ebook', 'If you only know the ebook by name, call list_ebooks first', 'metadata is the cheap way to inspect a design before changing it', and 'Read every page before replacing the body'. Exclusions and ordering constraints are stated, not inferred.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources