Skip to main content
Glama
Sign In

OrgGen AI

by ai.orggen
OverviewDiscussionsAdmin

reply_comment

Adds one message to an existing thread of the project the call targets, to answer a remark or continue a discussion. add_comment starts a new thread, resolve_comment closes one, delete_comment removes a whole thread with its messages (a single message cannot be retracted or edited by this tool); the thread ids are read with list_comments. Effects: the message is written, the thread's last-activity date moves, and the users named in mentions are notified, but only those with real access to the project: the others are dropped without any row and named in the response warning. A reply does not reopen a resolved thread (resolve_comment with resolved=false does). Returns messageId. REFUSED with an error, nothing written, when the thread does not exist or belongs to another project ('Thread not found in this project').

Input Schema

NameRequiredDescriptionDefault
bodyYesText of the reply (plain text, rendered as written, 1 to 5000 characters)
mentionsNoIDs of the mentioned users (max 20). Only those with REAL access to this project are notified; the others are silently dropped (no row created) and named in `warning`.
threadIdYesID of the thread to reply to (UUID, as returned by list_comments or add_comment)
expectedProjectIdNoUUID of the project targeted by THIS call. ACTUALLY targets this project instead of the session project. Refused without changing anything if access is not granted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / body / description
      Added value: +"Text of the reply (plain text, rendered as written, 1 to 5000 characters)"
    • changedInput schema / properties / threadId / description
      Previous value: -"Thread ID"New value: +"ID of the thread to reply to (UUID, as returned by list_comments or add_comment)"
  2. Changed3 schema fields changed
    • changedInput schema / properties / expectedProjectId / description
      Previous value: -"UUID du projet visé par CET appel. Cible RÉELLEMENT ce projet au lieu du projet de session. Refusé sans rien modifier si l'accès n'est pas accordé."New value: +"UUID of the project targeted by THIS call. ACTUALLY targets this project instead of the session project. Refused without changing anything if access is not granted."
    • changedInput schema / properties / mentions / description
      Previous value: -"IDs des utilisateurs mentionnés (max 20). Seuls ceux ayant un accès RÉEL à ce projet sont notifiés ; les autres sont écartés silencieusement (aucune ligne créée) et nommés dans `warning`."New value: +"IDs of the mentioned users (max 20). Only those with REAL access to this project are notified; the others are silently dropped (no row created) and named in `warning`."
    • changedInput schema / properties / threadId / description
      Previous value: -"ID du thread"New value: +"Thread ID"
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare the safe-write profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false); the description adds real behavioral detail on top: last-activity date moves, mentions notify only users with actual project access while others are silently dropped and surfaced in `warning`, returns `messageId`, and is REFUSED with nothing written when the thread is missing or belongs to another project.

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?

The core action is front-loaded in the first clause, and nearly every clause carries decision-relevant information (sibling routing, destruction limits, refusal rule). It is dense rather than bloated, with only minor redundancy against the schema's mentions wording.

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?

For a 4-parameter mutation tool with no output schema, the description covers side effects, notification semantics, the returned `messageId` and `warning`, the immutability of individual messages, and the failure mode. Nothing an agent needs to call it correctly is missing.

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 genuinely new semantics around threadId: where ids come from and the cross-project refusal ('Thread not found in this project'), which the schema does not state. It also reinforces the mentions drop-with-warning rule, though that largely duplicates the schema text.

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 ('Adds one message to an existing thread') plus the intent ('answer a remark or continue a discussion'), and immediately differentiates itself from add_comment, resolve_comment and delete_comment by naming what each sibling does instead.

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 routes between siblings: add_comment starts a new thread, resolve_comment closes one, delete_comment removes an entire thread, and thread ids come from list_comments. It also names the non-obvious exclusion — a reply does not reopen a resolved thread, resolve_comment with resolved=false does — so the agent knows when this tool is the wrong choice.

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

All OrgGen AI 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