Skip to main content
Glama

read_work

Read a work from the shelf. Without a section: its table of contents (with paragraph counts). With a section: that section's text, original and translation row by row, up to ~24k characters; if truncated, call again with paragraph = next_paragraph to read on. With find: every row in the work (or in one section) containing all search words in any order, accent- and breathing-insensitive (e.g. find "αλοω κατα ποντον" or "worse than a brother"), with section and paragraph to read it.

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": {
      "id": "<id>"
    },
    "name": "read_work"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes
findNoText to find inside the work, in any of its languages.
sectionNo
paragraphNoStart reading the section at this paragraph (1-based). Default 1.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does so well: it discloses the return shape per mode (TOC with paragraph counts, text original-and-translation row by row), the ~24k character ceiling, and the exact recovery path (call again with paragraph = next_paragraph). It does not mention failure behavior for a bad id or an out-of-range section, which keeps it short of a 5.

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

Conciseness5/5

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

One dense paragraph, zero filler, with the default mode front-loaded and each subsequent mode introduced by its selecting parameter. The examples inside the find clause justify their length by showing acceptable query syntax.

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

Completeness4/5

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

For a four-parameter read tool with no output schema, the description covers input branching, return content, truncation limits, and continuation. The residual gap is that next_paragraph is referenced as if it were a known output field, which an agent has to discover at runtime.

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 only 50%, with id and section undocumented in the schema, and the description compensates: section is explained through both usage modes, find is given matching semantics (all words, any order, accent- and breathing-insensitive) plus examples, and paragraph's continuation role is described. Only id is left to inference, which is reasonable but not zero-cost.

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

Purpose4/5

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

"Read a work from the shelf" names a specific verb and resource, and the three modes (no section, with section, with find) are spelled out precisely. It never names a sibling such as get_passage or search_shelf, so an agent must infer the boundary with those tools on its own.

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

Usage Guidelines4/5

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

The description gives clear parameter-driven routing: omit section for a table of contents, supply section for text, supply find for a word search, and combine find with section to narrow it. That is genuine when-to-use guidance, but there is no when-not guidance and no reference to an alternative tool for adjacent needs.

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