Skip to main content
Glama

Start a Review Shift

start_review_shift
Read-only

Start a volunteer REVIEW SHIFT: the user lends their Claude (you) to Source Library to check one book against its scans: by default its 10-page check, two facing pages from each fifth of the book, then reading on in order if the user wants. Use when the user wants to help Source Library, says "start a shift" or "review pages", or asks how they can contribute. The user does NOT need to read the book's language: YOU do the checking (scan against transcription, transcription against English) and the user starts the shift, chooses how many pages, watches and asks questions. Returns ONE page: its scan (inline image), our transcription, our English, the last lines of the previous page, and next (pass to continue_review_shift). Follow first_time once, then how_to_run on every page, working through the stretch of pages without stopping between them. With no book, it resumes the user's last run (pass volunteer_code) or picks a book that needs checking; book takes an id, slug or reader URL if the user names one; new_book true skips the resume. Run shifts only while the user is in this conversation; never set one up to run on a schedule or from a script.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "start_review_shift"
  }
}

Input Schema

NameRequiredDescriptionDefault
bookNoA book the user wants to check: id, slug or sourcelibrary.org reader URL (optional).
languageNoPrefer books in this original language, e.g. "Latin" (optional; any language works, the user need not read it).
new_bookNoTrue to start a different book instead of resuming the last one.
volunteer_codeNoThe code from the user's earlier shift, if they have one. Omit on a first shift; one is issued.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / book
      Added value: +{
      +  "description": "A book the user wants to check: id, slug or sourcelibrary.org reader URL (optional).",
      +  "type": "string"
      +}
    • changedInput schema / properties / language / description
      Previous value: -"Original language the user reads, e.g. \"Latin\", \"Greek\", \"Arabic\", \"German\", \"Chinese\", \"Tibetan\". Omit to accept any language, but ask the user first which languages they read."New value: +"Prefer books in this original language, e.g. \"Latin\" (optional; any language works, the user need not read it)."
    • addedInput schema / properties / new_book
      Added value: +{
      +  "description": "True to start a different book instead of resuming the last one.",
      +  "type": "boolean"
      +}
    • removedInput schema / properties / pages
      Removed value: -{
      -  "description": "How many pages (1-5, default 5).",
      -  "type": "number"
      -}
  2. Added

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered; the description goes well beyond that by disclosing the return payload (one page with scan, transcription, English, prior lines, and next pointer), the volunteer_code issuance, the resume-last-run default, and the first_time/how_to_run sequencing. Nothing in it contradicts the readOnly/idempotent hints — the shift is a read-and-return session, not a library mutation.

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?

Purpose and triggers are front-loaded, and nearly every sentence carries operational content. It is a single dense run-on paragraph, though, and the clause about the user 'chooses how many pages' sits awkwardly since no page-count parameter exists.

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?

With no output schema and four parameters, the description does the heavy lifting well: it describes the returned page contents, the resumption path, and the in-conversation-only constraint. The one loose end is the unexplained claim that the user chooses how many pages, which has no corresponding parameter and could leave an agent unsure how that choice is expressed.

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 100%, so the baseline is 3, but the description adds real meaning the schema does not: the precedence between book, volunteer_code and new_book (omit book to resume, new_book true skips the resume) is only explained in the prose. The language parameter is only lightly elaborated ('any language works, the user need not read it'), which the schema already covers.

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?

The description names a specific verb and resource ('Start a volunteer REVIEW SHIFT') and immediately explains the mechanic: lending the user's Claude to check one book against its scans with a 10-page check spread across the book. It also distinguishes itself from the closest sibling by naming continue_review_shift as the tool that receives the 'next' pointer.

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 triggers are given ('start a shift', 'review pages', 'asks how they can contribute'), along with the hand-off rule to continue_review_shift for subsequent pages. It also states a hard exclusion — never set a shift up to run on a schedule or from a script — and clarifies that the user need not read the book's language, removing a common reason an agent would hesitate to invoke it.

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.