update_appUpdate an existing application with a new prompt. The AI modifies the app based on your instructions. Creates a Saved Version before the update. Returns a job_id - poll get_job_status to track progress.
| Name | Required | Description | Default |
|---|---|---|---|
| app_id | Yes | The app ID to update | |
| prompt | Yes | What to change in the app |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the bare annotations (readOnlyHint=false, destructiveHint=false), the description discloses critical behavior: it creates a Saved Version before updating (providing rollback safety) and is asynchronous, requiring polling via get_job_status. These traits materially affect how an agent should call and interpret the tool, and they do not contradict any annotation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is four short sentences with zero fluff. It front-loads the core action, then adds three high-value behavioral details (AI modification, version snapshot, async tracking) in order of importance. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-parameter, no-output-schema tool, the description is complete: it explains what it does, how it behaves (asynchronous, creates checkpoint), and how to follow up. An agent has everything needed to invoke it correctly and interpret the response (job_id) without gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes both parameters at 100% coverage (app_id and prompt), so the baseline is 3. The description adds meaning by clarifying that the prompt is instructions to the AI, that the app is modified asynchronously, and that a Saved Version is created, giving extra context beyond the schema's plain property descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb+resource ('Update an existing application') and the mechanism ('with a new prompt'), clearly distinguishing it from siblings like create_app (for new apps) and update_ab_test. The phrase 'existing application' also limits scope, making the purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use it (for existing apps, not new ones) and notes it returns a job_id to track progress via get_job_status, which routes the agent to a sibling tool. It doesn't explicitly name alternatives or exclusions, but the context of updating an existing app is clear enough for correct selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly distinct purposes with detailed descriptions, but there are some overlapping pairs like read_app_file/read_app_files and create_entity_records vs seed_entity, which could cause misselection. Singular/plural variants and compatibility tools introduce minor ambiguity, but the majority are well-separated.
Tool names predominantly follow a consistent verb_noun pattern (e.g., create_app, get_entities, delete_secret). There are some variations like 'agency_create_client' and 'seed_entity' that deviate slightly, but the overall convention is predictable and readable.
With 82 tools, the server is far above the typical range and feels overwhelming. Even for a full platform API, the count is extreme and likely increases selection complexity. A more curated set would improve navigability without sacrificing capability.
The tool surface is exceptionally comprehensive, covering app lifecycle, file operations, entity CRUD, versioning, A/B testing, secrets, integrations, domains, agents, scheduling, policies, and member management. No obvious missing operations for the platform's scope; it even includes validation and workflow guidance tools.