Skip to main content
Glama

Message a research project

message_project

Send messages to a project's agents to add user context, answer questions, or request changes; attach files, and interrupt the current step when corrections are urgent.

Instructions

Write to a project's agents, with local files if any: answer in the user's own words, add context, or after a delivery ask for changes (a new round). While they work, they read it after the step they are on (usually seconds); deliver_now hands it over at once, interrupting that step. COSTS CREDITS: the turns it starts are charged by use.

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": {
      "project_id": "<project_id>",
      "text": "<text>"
    },
    "name": "message_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesThe message, in the user's words
filesNoAbsolute paths of files to add with it
project_idYesThe project id
deliver_nowNoInterrupt the step the agents are on so they read it at once (urgent corrections only)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.7.0

TDQS

A4/5.0
Behavior4/5

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

Beyond the thin write/non-destructive annotations, the description discloses the key dynamics: agents read the message after their current step (seconds), deliver_now interrupts that step, and the resulting turns consume credits. The credit warning is genuinely load-bearing for an agent deciding whether to send. It stops short of saying what is returned or what happens on failure, so a 4 rather than 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?

Four dense clauses, front-loaded with the core action and ending on the cost warning that most affects the decision. The mid-sentence parenthetical about reading "after the step they are on (usually seconds)" is slightly tangled but each clause carries real information, so it is efficient rather than padded.

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 four-parameter write tool with no output schema and only minimal annotations, the description covers the mechanics an agent needs: timing, interruption, cost, and the supported reasons to send. It does not describe the response shape or any per-call limits, which are the only remaining gaps.

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 timing semantics the schema lacks: normal messages are seen after the current step (usually seconds) while deliver_now preempts it. The files parameter is only loosely echoed ("with local files if any") and adds nothing to the schema's absolute-path note.

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?

"Write to a project's agents" gives a concrete verb and resource, and the three enumerated situations (answer in the user's own words, add context, request changes after a delivery) make the tool's role unmistakable. It is clearly the messaging channel rather than an action/execution tool, though no sibling is named to sharpen the boundary with act_on_project.

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?

It states concrete when-to-use conditions (replying to a delivery, adding context, opening a new round after a delivery) and a when-not constraint for the escalation flag: "urgent corrections only" for deliver_now. No named alternative tool is offered for cases where messaging is the wrong choice, which keeps it short of a 5.

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