Skip to main content
Glama

reply_to_comment

Replies to an existing review thread in an Overleaf project, posting the message and returning thread and message details; prevents blind retry after a timeout.

Instructions

Reply to an existing review thread. An unknown threadId fails with NOT_FOUND and posts nothing. Returns threadId and the created message (id, author { id, displayName }, content, ISO timestamp), plus trackChangesActive and writeMode. A timed-out reply is never resubmitted: it returns recoveredAfterTimeout when the thread shows exactly one new matching message from this account, else OUTCOME_UNKNOWN; do not retry it blindly.

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>",
      "threadId": "<threadId>",
      "content": "<content>"
    },
    "name": "reply_to_comment"
  }
}

Input Schema

NameRequiredDescriptionDefault
contentYes
threadIdYesExisting thread id from list_comments
projectIdYesOverleaf project ID

Output Schema

NameRequiredDescriptionDefault
messageYes
threadIdYes
writeModeYes
trackChangesActiveYes
recoveredAfterTimeoutNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

A4.1/5.0
Behavior5/5

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

Annotations only declare idempotentHint=false and destructiveHint=false; the description goes well beyond by disclosing the NOT_FOUND failure mode with no side effects, the recovery semantics (recoveredAfterTimeout vs OUTCOME_UNKNOWN), and an explicit no-blind-retry warning that matches the non-idempotent annotation.

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-loads the purpose, then layers failure behavior, return shape, and retry safety in order. Dense but each sentence carries information; the parenthetical return-field enumeration is the only part that partly overlaps the output schema.

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 non-idempotent write with a tricky timeout path, the description covers the failure and recovery cases that matter most. Some return-value detail duplicates the existing output schema, which slightly weakens the payoff of that sentence.

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 67% and threadId/projectId already carry descriptions; the description only reinforces that threadId must reference an existing thread. It says nothing about the 'content' parameter beyond what minLength:1 already conveys (format, markdown vs plain text, length expectations), so schema does most of the work.

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?

States a specific verb+resource: 'Reply to an existing review thread.' An agent can tell this posts a message into a thread rather than creating one (add_comment) from the 'existing ... thread' framing, though no sibling is named explicitly and the add_comment contrast is left implicit.

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?

Gives concrete operational guidance: an unknown threadId fails with NOT_FOUND and posts nothing, and a timed-out reply must not be retried blindly. It lacks an explicit 'use this instead of add_comment' routing sentence, keeping it below a 5.

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