Skip to main content
Glama

Push edits to draft

push_board
DestructiveIdempotent

Apply file changes to your open editing draft: text, exact edits, delete, rename, or a declared large binary. Deletes and replacements change the current draft; earlier checkpoints stay restorable. If a change needs edits you cannot state exactly, give a change plan instead. Retry with the same operationId. If upload links come back, PUT each within 5 min, then repeat the same call, which renews expired links. Never show them.

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": {
      "board": "<board>",
      "operationId": "<operationId>",
      "expectedCheckpointId": "<expectedCheckpointId>",
      "changes": "<changes>"
    },
    "name": "push_board"
  }
}

Input Schema

NameRequiredDescriptionDefault
boardYesYour board: handle/slug or a boardrepo.com URL.
changesYesFile changes against the current checkpoint, one entry per file. Combine renameTo with content, edits or upload in the same entry.
operationIdYesClient-generated UUID. Reuse for retries of the same logical step; use a new one for a new edit or save.
expectedCheckpointIdYescheckpoint.id from get_current_work.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true; the description adds what those mean in practice — deletes and replacements alter the current draft while earlier checkpoints stay restorable, and idempotency is realized through operationId reuse. The upload-link lifecycle (5-minute expiry, PUT, re-push to renew) is genuinely useful context, though 'Never show them' is an unexplained instruction without a stated reason.

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-loaded with the core action and the mutation scope, then the retry and upload mechanics. Sentences are dense but each carries information; the only weak line is the clipped 'Never show them', which lacks a clear referent and rationale.

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?

An output schema exists, so return values need not be spelled out, and the description still covers the one output behavior that affects the call sequence (upload links). The main gap is the unexplained 'change plan' alternative, which points at a workflow the reader cannot resolve from this definition alone.

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 description coverage is 100%, so the schema already explains board, changes, operationId and expectedCheckpointId in detail. The description reinforces the operationId retry rule and the upload-then-repeat loop, but adds no syntax or constraint detail the schema does not already carry; baseline 3 applies.

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 and resource: applying file changes (text, exact edits, delete, rename, declared binary) to the open editing draft. The change-type list makes the scope concrete, but it never names a sibling, so the boundary with commit_board_upload, restore_checkpoint, or create_upload_link has to be inferred.

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 real operational guidance: retry with the same operationId, fall back to a change plan when exact edits cannot be stated, and the two-step upload-link sequence with a 5-minute window and renewal by repeating the call. It does not say when to prefer a sibling tool over this one, and 'give a change plan instead' names no concrete tool or parameter.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources