Skip to main content
Glama

busabase

by com.busabase
OverviewDiscussionsAdmin

Propose file changes inside a Skill, Drive, or AirApp node

node_files_change_request

Propose file changes inside a Skill, Drive, or AirApp node

Review is permission-aware, decided server-side: the change merges immediately when your key has write access on the node and lands as a pending ChangeRequest otherwise — check the response's status. Pass requireReview to always propose instead — worth doing for a batch containing a delete, since that removes a mounted file (its previous bytes stay in the change request's history, and a batch is never partially merged). Each operation is one of create / update / delete / metadata_update. Include baseContentHash (from node_file_read) on an update so a concurrent edit is caught. For kind "airapp", keep the project runnable by npm run dev — editing package.json must leave a "dev" script starting a plain Node server, not a bundler dev server.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindYesWhich file-tree node kind to act on.
nodeIdYesId of the node.
messageNoExplanation for the reviewer. Conventional-commit style, e.g. "Rewrite README quickstart for the new auth flow".
playbookNoOptional. The playbook you are following, as `kind:nodeId[:key]` from playbooks_search (e.g. `prompt:nod_123:log-visit`). Recorded on the change request so the person can see which playbook produced it.
autoMergeNoSkip review and apply the file changes immediately if you have write access. Not a permission override, and ignored for a batch containing a delete. Default is permission-aware: merge when you can, otherwise propose.
operationsNoFile operations, e.g. [{"kind":"update","path":"SKILL.md","content":"...","baseContentHash":"..."}].
submittedByNoProducer label recorded on the change.
requireReviewNoAlways propose a pending ChangeRequest, even with write access.
targetSpaceIdNoBusabase space id. Call auth_verify first and ask the user which space to use when more than one is returned.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / playbook
      Added value: +{
+  "description": "Optional. The playbook you are following, as `kind:nodeId[:key]` from playbooks_search (e.g. `prompt:nod_123:log-visit`). Recorded on the change request so the person can see which playbook produced it.",
+  "type": "string"
+}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only mark readOnlyHint=false, openWorldHint=false, and destructiveHint=false, so they do not disclose the nuanced behavior. The description adds critical traits: merge-vs-pending depends on write access, a batch is never partially merged, delete retains previous bytes in history, and the response status must be checked. This substantially exceeds annotation coverage.

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?

Every sentence earns its place: purpose, permission behavior, operation kinds, concurrency, and airapp constraint. The description is dense but front-loaded and free of filler.

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 tool with no output schema, the description covers the important behavioral and operational context: status checking, merge semantics, delete safety, concurrency, and airapp runnability. It does not spell out the full response shape or error cases, but the schema and the status pointer are adequate.

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?

The input schema covers 100% of parameters, including detailed autoMerge and requireReview descriptions, so the baseline is 3. The description adds value by enumerating operation kinds (create/update/delete/metadata_update), explaining baseContentHash's source and purpose, and giving rationale for requireReview on deletes. It does not fully document operations construction, but the schema example covers that.

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 opens with a specific verb and resource: 'Propose file changes inside a Skill, Drive, or AirApp node.' This clearly scopes the tool to file-level change requests on those node kinds, distinguishing it from sibling change-request tools like bases_create_change_request and record_change_request. The title reinforces the same scope, so an agent can identify the right tool without opening the schema.

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?

The description gives concrete decision rules: review is permission-aware and server-side, requireReview forces a pending request and is recommended for batches containing a delete, and baseContentHash should be included on updates to catch concurrent edits. It also provides airapp-specific constraints. It does not explicitly name sibling alternatives, but the scope and option-level guidance are clear.

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

All busabase 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