Skip to main content
Glama

Act on a research project

act_on_project

Take an allowed project action—confirm a plan, answer questions, top up credits, pause or resume, send feedback, or deliver now—using the project ID and action IDs.

Instructions

Take one of the project's allowed_actions, with the ids it names: confirm_plan (spec_version; starts the paid work - only once the user agreed to the plan; it is charged by what it uses), answer (answers: question id -> answer), top_up (pause_id; max_credits raises a credit cap that ran out), one_more_round, accept_as_is, pause, resume, cancel, feedback (version, value), deliver_now (the agents read the waiting messages at once, interrupting the step they are on). COSTS CREDITS for confirm_plan, top_up, one_more_round and the scoping answers.

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>",
      "action": "<action>"
    },
    "name": "act_on_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNofeedback: what to change
valueNofeedback: the verdict
actionYesOne of the allowed_actions get_project listed
answersNoanswer: question id -> answer
versionNofeedback: the delivered version
pause_idNotop_up: the pause it continues
project_idYesThe project id
max_creditsNoconfirm_plan, top_up, one_more_round: a higher credit cap for the whole project, agreed by the user
spec_versionNoconfirm_plan: the plan version shown to the user

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.7.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds substantial context beyond that: which actions consume credits, that confirm_plan starts paid work, that top_up raises an exhausted credit cap, and that deliver_now interrupts the agents' current step. Gaps remain for a state-changing dispatcher: it never says whether pause/cancel are reversible or what happens to in-flight work on cancel.

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 imperative and the source of valid actions are front-loaded, and each parenthetical carries operational information rather than filler. The dense run-on enumeration is harder to scan than a short list, but nothing is clearly redundant.

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 9-parameter action dispatcher with a nested answers object and no output schema, the description covers most action/parameter pairings and the credit implications. It leaves two notable holes: extend_retention is never described, and the description says nothing about what the call returns (e.g., updated project state, job id, remaining credits).

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 the action-to-parameter binding the schema cannot express (confirm_plan takes spec_version, top_up takes pause_id, feedback takes version+value, answer takes question-id map). It also clarifies max_credits semantics ("raises a credit cap that ran out") beyond the schema's wording, though it omits the schema's extend_retention action entirely.

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 concrete verb ("Take one of the project's allowed_actions") plus the resource (a project) and then enumerates the full action vocabulary, so an agent knows exactly what this tool does. It is clearly distinct from read-only siblings like get_project (which supplies allowed_actions) and message_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 gives a real precondition for the riskiest action ("confirm_plan ... only once the user agreed to the plan") and implies the sequence by tying the action value to what get_project listed. It stops short of explicitly naming alternatives or stating when-not to use this tool (e.g., prefer message_project for free-form contact).

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