Skip to main content
Glama

Update application demo config

update_application_demo_config
Destructive

Replace an Application's saved demo env entries and throwaway-database flag wholesale (the demo pre-setup every future launch inherits). Read the current configuration first and carry existing env entries forward - entries not in this call are dropped. The full-stack stack profile and shared base stack designations are NOT settable here and are preserved untouched: a demo whose database comes from a stack must not have the throwaway Postgres wired over it. Values may reference ${{ ankra.demo_database.* }} placeholders (requires database=true) and ${SECRET_SLOT:} sentinels (kept secret, mounted via a Kubernetes Secret). Affects only demo deployments in TTL-reaped namespaces, never production workloads; running demos pick the change up on their next redeploy_demo.

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": {
      "application_id": "<application_id>",
      "env": "<env>",
      "database": "<database>"
    },
    "name": "update_application_demo_config"
  }
}

Input Schema

NameRequiredDescriptionDefault
envYesThe complete demo environment as a name-to-value object (empty object clears it). Values carrying ${SECRET_SLOT:<uuid>} sentinels are stored as secret entries.
routingNoHow a multi-component demo is published on the preview host: which component serves / and where the others are routed. Omit to preserve the saved declaration; pass null to clear it and return every lane to the heuristic.
databaseYesProvision a throwaway per-demo Postgres on every launch and enable the ${{ ankra.demo_database.* }} placeholders. Required.
protectedNoSwitch Ankra's edge password guard for every demo of this application. Omit to preserve the stored setting. Turning it on mints one shared credential (username 'preview') and this call's answer carries generated_password; Ankra also keeps it in its secret store, so a member can copy it again later from the application's previews in the Ankra UI. Turning it off clears the credential and drops the kept copy. Enforced at the ingress by a Traefik basicAuth Middleware, never inside the application, so the staging cluster needs the Traefik ingress: without it a protected launch fails closed rather than publishing open.
application_idYesThe Application whose demo configuration to replace.
migrate_commandNoThe command that provisions a fresh demo database's schema (for example 'pnpm run db:migrate' or 'alembic upgrade head'). Runs through sh -c in the application image after the database is reachable, with the demo environment exported. Omit to preserve the saved command; pass an empty string to clear it. Requires database=true or a base stack.
database_extensionsNoPostgres extensions the demo database creates at initdb (for example ["vector"]). Plain lowercase identifiers only. Omit to preserve; pass [] to clear. Requires database=true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Annotations only say destructive, non-idempotent and not read-only; the description goes well beyond that by stating entries are dropped wholesale, that stack-sourced databases must not have throwaway Postgres wired over them, that turning on the password guard mints a credential returned as generated_password, and that a missing Traefik ingress makes protected launches fail closed. It also scopes impact to TTL-reaped demo namespaces and never production.

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 destructive wholesale-replace semantic is front-loaded and every sentence carries operational content (preservation rules, placeholder syntax, blast radius, redeploy timing). Some sentences are overloaded with parenthetical asides, making it denser than needed for a single paragraph.

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 destructive 7-param tool with no output schema, the description covers the main hazards, side effects and the one returned value that matters (generated_password). The gap is that the opening sentence implies this tool only touches env and the database flag, leaving routing/protected/migrate_command scope to the schema for an agent skimming only the description.

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 100%, so the baseline is 3; the description still earns a bump by explaining that ${{ ankra.demo_database.* }} placeholders require database=true and that ${SECRET_SLOT:<uuid>} sentinels are stored as secrets mounted via a Kubernetes Secret. It does not add anything about routing, protected, migrate_command or database_extensions beyond what the schema already documents.

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?

"Replace an Application's saved demo env entries and throwaway-database flag wholesale" gives a specific verb and resource with a clear scope qualifier ("the demo pre-setup every future launch inherits"). It falls short of 5 because the opening frame names only env and database while the schema also accepts routing, protected, migrate_command and database_extensions, so the stated purpose is narrower than the tool's actual surface, and no sibling is named directly.

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?

It gives a concrete pre-call workflow ("Read the current configuration first and carry existing env entries forward") and an explicit exclusion (the stack profile and shared base stack designations are NOT settable here), plus a follow-up path ("next redeploy_demo"). It stops short of 5 because it never names the read sibling (get_application_demo_config) or the stack-profile tool an agent should use instead.

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.