Skip to main content
Glama

Source Library

by io.github.Embassy-of-the-Free-Mind
OverviewDiscussionsAdmin

Submit a Page Review

submit_page_review

Record the verdict on one page of a shift. mode "book-run" (start_review_shift / continue_review_shift): the verdict and findings are YOURS, from reading the scan and both texts; set user_looked true if the user checked anything on the page themselves. mode "blind" (start_blind_check): the verdict is the USER'S, given before your reading; put yours in assistant_verdict. Verdicts: both_sound (transcription matches the scan and the English matches the original), translation_drift (transcription right, English departs from it), transcription_off (the text does not match the scan), both_off, unclear (the scan or the text cannot be judged). Quote exact words in every finding. A review is evidence about the page; it does not change it.

Input Schema

NameRequiredDescriptionDefault
modeNo"book-run" unless the page came from start_blind_check.
nameNoHow the user wants to be credited (optional).
noteNoAnything a later reader should know (optional, max 2000 chars).
book_idNorun.book_id (book run)
item_idYespage.item_id (book run) or the item's item_id (blind check)
verdictYesbook-run: your verdict. blind: the user's final verdict.
shift_idNoshift_id (blind check only)
page_numberNopage.page_number (book run)
user_lookedNobook-run: true if the user checked something on this page themselves.
text_versionNopage.text_version, passed back unchanged.
first_verdictNoblind: the user's verdict before your reading, if it changed.
volunteer_codeYes
assistant_modelYesYour own model name and version, copied exactly as your instructions or system prompt give it, and whether extended thinking is on. Write "unknown" rather than guess; a wrong name is worse than none.
reader_languagesNoLanguages the user says they read, if they said.
assistant_verdictNoYour own verdict (blind mode; in book-run it equals verdict).
assistant_findingsNoProblems found, each with an exact quote (max 12).
verdict_before_assistantNoblind: true if the user committed to a verdict before seeing your reading.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed19 schema fields changed
    • changedInput schema / properties / assistant_findings / description
      Previous value: -"Problems you pointed out, each with the user's response (max 12)."New value: +"Problems found, each with an exact quote (max 12)."
    • changedInput schema / properties / assistant_findings / items / properties / problem / description
      Previous value: -"What is wrong (max 500 chars)"New value: +"What is wrong, and what the scan or original shows (max 500 chars)"
    • addedInput schema / properties / assistant_findings / items / properties / user_agreed / description
      Added value: +"Only if the user actually weighed in on this point"
    • changedInput schema / properties / assistant_model / description
      Previous value: -"Your model name, if known (for analysis only)."New value: +"Your own model name and version, copied exactly as your instructions or system prompt give it, and whether extended thinking is on. Write \"unknown\" rather than guess; a wrong name is worse than none."
    • changedInput schema / properties / assistant_verdict / description
      Previous value: -"Your own verdict on the page."New value: +"Your own verdict (blind mode; in book-run it equals verdict)."
    • addedInput schema / properties / book_id
      Added value: +{
+  "description": "run.book_id (book run)",
+  "type": "string"
+}
    • changedInput schema / properties / first_verdict / description
      Previous value: -"The verdict the user gave before your reading, if it differs from the final one."New value: +"blind: the user's verdict before your reading, if it changed."
    • changedInput schema / properties / item_id / description
      Previous value: -"item_id from start_review_shift"New value: +"page.item_id (book run) or the item's item_id (blind check)"
    • addedInput schema / properties / mode
      Added value: +{
+  "description": "\"book-run\" unless the page came from start_blind_check.",
+  "enum": [
+    "book-run",
+    "blind"
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / note / description
      Previous value: -"The user's own words on what is wrong or uncertain (optional, max 2000 chars)."New value: +"Anything a later reader should know (optional, max 2000 chars)."
    • addedInput schema / properties / page_number
      Added value: +{
+  "description": "page.page_number (book run)",
+  "type": "number"
+}
    • changedInput schema / properties / reader_languages / description
      Previous value: -"Languages the user says they read, e.g. \"Latin, Italian\"."New value: +"Languages the user says they read, if they said."
    • changedInput schema / properties / shift_id / description
      Previous value: -"shift_id from start_review_shift"New value: +"shift_id (blind check only)"
    • changedInput schema / properties / text_version / description
      Previous value: -"text_version from the item, passed back unchanged."New value: +"page.text_version, passed back unchanged."
    • addedInput schema / properties / user_looked
      Added value: +{
+  "description": "book-run: true if the user checked something on this page themselves.",
+  "type": "boolean"
+}
    • changedInput schema / properties / verdict / description
      Previous value: -"The user's final verdict."New value: +"book-run: your verdict. blind: the user's final verdict."
    • changedInput schema / properties / verdict_before_assistant / description
      Previous value: -"True if the user committed to a verdict before seeing your reading."New value: +"blind: true if the user committed to a verdict before seeing your reading."
    • removedInput schema / properties / volunteer_code / description
      Removed value: -"volunteer_code from start_review_shift"
    • changedInput schema / required
      Previous value: -[
-  "item_id",
-  "volunteer_code",
-  "verdict",
-  "verdict_before_assistant"
-]New value: +[
+  "item_id",
+  "volunteer_code",
+  "verdict",
+  "assistant_model"
+]
  2. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare write semantics (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the safety profile is covered. The description adds meaningful semantics beyond that: a review is an evidence record that "does not change" the page, and findings must quote exact words. It does not describe what happens on duplicate submits or failure modes, so it stops 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.

Conciseness4/5

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

A single dense paragraph that front-loads the core action before branching into mode-specific rules and verdict vocabulary. It is efficient, though the run-on mode/verdict enumeration would be easier to scan if split into labeled lines.

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 17-parameter tool with nested findings objects and no output schema, the description covers the mode-dependent branching, verdict taxonomy, and quoting requirement well. It omits error/retry behavior and duplicate-submission handling (relevant given idempotentHint=false), which keeps it just shy of complete.

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 description coverage is 94%, so the baseline is 3, but the description adds cross-field meaning that the schema documents in isolation: the relationship between verdict, first_verdict, assistant_verdict, and verdict_before_assistant under each mode, plus the requirement that findings quote source words. This is genuine added value over per-field descriptions.

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 ("Record the verdict on one page of a shift") and immediately differentiates the two operating modes by naming the sibling tools that produce each (start_review_shift/continue_review_shift vs start_blind_check). An agent can distinguish this from share_findings and propose_correction without opening any schema.

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?

Explicitly ties each mode to its originating sibling tool and specifies whose verdict applies in each case ("mode 'book-run'... the verdict and findings are YOURS" vs "mode 'blind'... the verdict is the USER'S"). It also states the precondition for user_looked and where the assistant's own verdict goes when it differs.

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

All Source Library toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources