Skip to main content
Glama
Sign In
cohors

cohors

by rushirb2001
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

Write a repo's launchpad file

write_repo_contribution
DestructiveIdempotent

Validate and write a repo's .cohors/repo.json as a full replacement, returning all errors at once and writing nothing when invalid. Read the current file first to preserve tasks and flows.

Instructions

Validate and write one repo's .cohors/repo.json (its flows, agents, tasks). REPLACES the whole document: read the current one with launchpad first and pass back everything you mean to keep, especially tasks the user is part-way through. Writes nothing when invalid and returns every error at once. Declare a flow only when it adds what detection cannot infer (a label, port, primary, composite command, cwd) — an empty flows array is a correct answer. Never set a task done without evidence. Nothing machine-specific: this file is committed. Also gitignores .cohors/local.json. Requires --allow-launchpad; dry_run validates without it.

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": {
      "repo": "<repo>",
      "name": "<name>"
    },
    "name": "write_repo_contribution"
  }
}

Input Schema

NameRequiredDescriptionDefault
iconNo
nameYesDisplay name.
repoYesRepo id, name/alias, or path (must be inside the fleet).
flowsNo
groupNoFree text; groups repos on the launchpad.
linksNo
tasksNo
agentsNo
dry_runNoValidate and report without writing (works without --allow-launchpad).
summaryNoOne line: what this repo IS.
generatedFromNoShort SHA of the commit you read, so staleness can be shown.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Goes well beyond the destructiveHint/idempotentHint annotations: it warns that the call REPLACES the whole document (so omitted items are lost), that nothing is written when invalid and all errors are returned at once, that the file is committed so nothing machine-specific belongs in it, and that the call also gitignores .cohors/local.json — a side effect no structured field discloses.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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

The most destructive fact (REPLACES the whole document) is front-loaded in sentence one, followed by the recovery procedure and then the guardrails. Sentences are dense but each carries a distinct instruction — validation behavior, flow-declaration policy, task-evidence rule, commit hygiene, side effects, and the flag requirement.

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 destructive whole-document writer with no output schema, this is complete: loss semantics, validation/error behavior, permission prerequisite, side effects, and content policy are all covered. An agent has everything needed to call it safely on the first attempt.

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 55% across 11 parameters, so the description has to carry some weight. It adds real semantics for the highest-risk fields — flows (when a declaration is warranted, and that empty is valid) and tasks (evidence requirement before status done) — plus dry_run behavior; the low-risk fields (icon, group, links, summary, generatedFrom) are left to the schema and are mostly self-describing.

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 pair (validate and write) and an exact resource (one repo's .cohors/repo.json), and names its contents (flows, agents, tasks). It also implicitly routes the agent to the sibling `launchpad` as the read counterpart, so the operation is distinguishable without opening a 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?

Explicit when-to guidance: read with `launchpad` first and pass back anything you intend to keep; declare a flow only when it adds what detection cannot infer; an empty flows array is a correct answer; never mark a task done without evidence. It also states the prerequisite (--allow-launchpad) and the escape hatch (dry_run validates without it).

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

Deploy Server

Other Tools