Skip to main content
Glama
delimit-ai

delimit

Official
by delimit-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Delimit Deploy Build

delimit_deploy_build

Build container images for an app at a specific git ref after deployment planning succeeds, producing SHA-tagged local images ready for the publish step.

Instructions

Build container images for an app at a specific git ref (Pro).

When to use: as the second step of the deploy chain after delimit_deploy_plan has succeeded and you need SHA-tagged container images locally before delimit_deploy_publish pushes them to the registry. The full chain is plan -> build -> publish -> verify -> (rollback on failure). When NOT to use: to push existing images to a registry (use delimit_deploy_publish), to deploy a site (delimit_deploy_site), to publish an npm package (delimit_deploy_npm), or to start the full chain (delimit_deploy_plan).

Sibling contrast: deploy_plan plans, this builds local images, deploy_publish pushes to the registry, deploy_verify checks rollout health, deploy_rollback reverts. Compared to delimit_deploy_site (static-site deploy) and delimit_deploy_npm (npm publish), this is the container path.

Side effects: gated by require_premium — unlicensed callers receive a license payload and no build runs. On a licensed call, invokes backends.deploy_bridge.build which shells out to the local container builder (e.g. docker buildx) — this consumes local disk for image layers and CPU for the build. No network push at this step (that is delivery_publish). The response is routed through _with_next_steps.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
appNoApplication name (project key in the deploy backend).
git_refNoGit ref (branch/tag/SHA). Default None = backend HEAD.
repo_pathNoExplicit Git worktree root.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv4.13.2
    • addedInput schema / properties / repo_path
      Added value: +{
+  "default": "",
+  "description": "Explicit Git worktree root.",
+  "type": "string"
+}
  2. Changed2 schema fields changedv4.7.9
    • addedInput schema / properties / app / description
      Added value: +"Application name (project key in the deploy backend)."
    • addedInput schema / properties / git_ref / description
      Added value: +"Git ref (branch/tag/SHA). Default None = backend HEAD."
  3. Changed2 schema fields changedv4.5.5
    • addedInput schema / properties / app / default
      Added value: +""
    • removedInput schema / required
      Removed value: -[
-  "app"
-]
  4. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

The description goes well beyond the annotations. It discloses the premium gating behavior ('require_premium — unlicensed callers receive a license payload and no build runs'), the internal backend invocation, the local resource consumption (disk and CPU), that no network push happens at this step, and that the response is routed through _with_next_steps. This is rich behavioral context that annotations do not provide.

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 description is detailed but relevant, with clear section headers and front-loaded purpose. The 'Sibling contrast' section is somewhat redundant with the 'When NOT to use' section, repeating similar routing guidance. Still, it earns a 4 because every section serves a clear decision-making purpose and the organization is effective.

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?

Given the tool has an output schema, a complete set of 3 parameters, and rich context about the deploy chain, prerequisites, side effects, and alternatives, nothing critical is missing. The description covers licensing gate, resource impact, chain position, and routing behavior. An agent has enough to decide when and how to invoke it correctly.

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 each parameter (app, git_ref, repo_path) is already documented in the schema. The description adds context around the git_ref default ('Default None = backend HEAD') but mostly relies on the schema. A baseline of 3 is appropriate since the schema covers parameter meaning adequately.

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 states a specific verb+resource ('Build container images for an app at a specific git ref') and distinguishes itself from siblings by naming the deploy chain step. It clearly identifies this as the build step producing local SHA-tagged images, not the plan or publish step.

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?

Provides explicit 'When to use', 'When NOT to use', and a full chain (plan -> build -> publish -> verify -> rollback). It names the alternative tools (delimit_deploy_publish, delimit_deploy_site, delimit_deploy_npm) and explains when they are appropriate instead. The sibling contrast section reinforces the routing decision clearly.

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