Skip to main content
Glama

Read a passage of a space file

read_passage
Read-onlyIdempotent

Read one passage by ID or a file's passages at a place, returning text with neighboring passage IDs so you can continue reading.

Instructions

Read one passage of a space file by its id from search_space_files, or a file's passages at a place (file_id + range, e.g. a whole page). Returns the text with the ids of the passages before and after it, to keep reading.

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": {
      "space_id": "<space_id>"
    },
    "name": "read_passage"
  }
}

Input Schema

NameRequiredDescriptionDefault
rangeNoWith file_id: the place, e.g. "p. 12", "slide 4", "section 3", "12:30" or "lines 40".
file_idNoInstead of passage_id: a file id from read_space, with range.
space_idYes
passage_idNoA passage id from search_space_files (or a previous/next id).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.6.5
    • changedInput schema / properties / range / description
      Previous value: -"With file_id: the place, e.g. \"p. 12\", \"slide 4\", \"12:30\" or \"lines 40\"."New value: +"With file_id: the place, e.g. \"p. 12\", \"slide 4\", \"section 3\", \"12:30\" or \"lines 40\"."
  2. First observedv0.6.1

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuine behavioral value that annotations can't: it says the return payload includes the text plus the ids of the preceding and following passages, which is the key fact for continuing a read. It does not say what happens when the requested range matches no passages or when a passage_id is stale.

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?

Two compact sentences with the primary mode first and the alternative second, and no filler. The parenthetical examples are load-bearing rather than padding, though the sentence is dense enough that the mutual exclusivity of the two modes has to be inferred.

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?

There is no output schema, so describing the returned text plus neighboring passage ids is exactly the missing piece, and the description supplies it. Combined with annotations covering safety and a 75%-documented schema, the only residual gap is error/precedence behavior, which is minor for a read-only tool.

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

Parameters3/5

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

Schema coverage is 75%, so most parameters are documented in the schema already, and the description largely restates the two usage modes (id-from-search vs file_id+range). It adds a little meaning by framing range as 'a place, e.g. a whole page', but gives no format examples beyond what the schema's range description already lists.

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 (read) and resource (one passage of a space file), and explicitly covers both addressing modes: by passage id or by file_id + range. It also distinguishes itself from the id-producing sibling search_space_files, so an agent can tell what it does and where its inputs come from.

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 routes usage well by naming the upstream source of each id: passage_id comes from search_space_files and file_id comes from read_space. What it doesn't state is precedence — what happens if both passage_id and file_id/range are supplied, or neither — and there is no explicit 'do not use this to read a whole file' exclusion.

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