Skip to main content
Glama
delimit-ai

delimit

Official
by delimit-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Delimit Deploy Verify

delimit_deploy_verify

Check a new deployment's health immediately after rollout to confirm it's healthy before finalizing; initiate rollback if unhealthy.

Instructions

Probe a freshly-deployed revision's health — experimental (Pro).

When to use: immediately after delimit_deploy_publish has rolled out a new revision, to confirm the new SHA is actually healthy before declaring the deploy done and closing out the chain (delimit_deploy_verify -> delimit_evidence_collect -> delimit_ledger_done -> delimit_notify). If this returns unhealthy, the next step is delimit_deploy_rollback. When NOT to use: for steady-state runtime health checks (use delimit_obs_status / delimit_obs_metrics), to read deploy-system metadata only (delimit_deploy_status), or for a smoke test before deploy (delimit_test_smoke).

Sibling contrast: delimit_deploy_status reads deploy-system metadata only; this actively probes the running deployment. delimit_obs_status is the steady-state observability surface; this is post-deploy-only.

Side effects: gated by require_premium — unlicensed callers receive a license payload and no probe runs. On a licensed call, invokes backends.deploy_bridge.verify which performs network health checks against the deployed app (HTTP probes, container inspection, dependency reachability). No write. Marked EXPERIMENTAL — health logic may return partial results on backends without health endpoints; do not treat as authoritative for runtime SLOs.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
appNoApplication identity; selects only this app's targets.
envNoTarget environment ("staging" or "production").
git_refNoOptional git ref the deploy targets.
repo_pathNoExplicit Git worktree root containing deploy target configuration.
observationNoOptional observation dict (unit/host/pid/cmdline/environ/exec_start/observed_at/health) or JSON string.
target_urlsNoOptional app-specific HTTPS targets; never expands to the global fleet.
service_unitNoOptional intended systemd unit for deployment binding.
expected_hostNoOptional intended host for deployment binding.
intended_releaseNoOptional exact sha/tag under test for deployment binding (LED-5321 M4).
deployment_healthNoOptional startup/semantic health dict or JSON string.
observation_max_age_sNoMax observation age in seconds (default 300).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv4.19.1
    • addedInput schema / properties / deployment_health
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional startup/semantic health dict or JSON string."
+}
    • addedInput schema / properties / expected_host
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional intended host for deployment binding."
+}
    • addedInput schema / properties / intended_release
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional exact sha/tag under test for deployment binding (LED-5321 M4)."
+}
    • addedInput schema / properties / observation
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional observation dict (unit/host/pid/cmdline/environ/exec_start/observed_at/health) or JSON string."
+}
    • addedInput schema / properties / observation_max_age_s
      Added value: +{
+  "default": 300,
+  "description": "Max observation age in seconds (default 300).",
+  "type": "integer"
+}
    • addedInput schema / properties / service_unit
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional intended systemd unit for deployment binding."
+}
  2. Changed3 schema fields changedv4.13.2
    • changedInput schema / properties / app / description
      Previous value: -"Application name."New value: +"Application identity; selects only this app's targets."
    • addedInput schema / properties / repo_path
      Added value: +{
+  "default": "",
+  "description": "Explicit Git worktree root containing deploy target configuration.",
+  "type": "string"
+}
    • addedInput schema / properties / target_urls
      Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional app-specific HTTPS targets; never expands to the global fleet."
+}
  3. Changed3 schema fields changedv4.7.9
    • addedInput schema / properties / app / description
      Added value: +"Application name."
    • addedInput schema / properties / env / description
      Added value: +"Target environment (\"staging\" or \"production\")."
    • addedInput schema / properties / git_ref / description
      Added value: +"Optional git ref the deploy targets."
  4. Addedv4.5.5

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false and destructiveHint=false, which is thin. The description compensates richly: it discloses the license gate (require_premium), the no-write guarantee, the internal backend invoked (backends.deploy_bridge.verify), the types of network checks performed, and the experimental caveat about partial results on backends without health endpoints. This goes well beyond what annotations provide and does not contradict them.

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 longer than average but every section earns its place: purpose, when/when-not, sibling contrast, side effects, and experimental caveat. It is front-loaded with the core purpose and uses clear section labels. Slightly verbose in the sibling contrast section, which repeats some when-not content, but overall efficient for the complexity it covers.

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 an 11-parameter, 0-required tool with an output schema, the description covers the essential operational context: when to call it, what it does internally, what it does not do, license gating, and reliability caveats. The output schema exists, so return-value documentation is not the description's burden. Nothing critical is missing for an agent to decide whether and how to invoke this tool.

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 baseline is 3. The description does not add parameter-level detail beyond the schema, but it does add context that helps interpret parameters: it explains that target_urls 'never expands to the global fleet' and that intended_release is the 'exact sha/tag under test'. However, most parameter semantics are already fully documented in the schema, so the description's marginal contribution is modest.

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 ('Probe'), a clear resource ('freshly-deployed revision's health'), and a scope qualifier ('experimental (Pro)'). It explicitly contrasts with delimit_deploy_status and delimit_obs_status, making sibling differentiation unambiguous. The purpose is immediately actionable.

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 ('immediately after delimit_deploy_publish'), when-not-to-use (steady-state checks, metadata-only reads, pre-deploy smoke tests), and names the exact alternative tools for each excluded case. It also names the next step (delimit_deploy_rollback) on unhealthy results, which is strong routing guidance.

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