gc_onboarding

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It lists many actions but does not explain what side effects occur (e.g., does 'reset' destroy data? does 'bootstrap_apex' create persistent resources? what happens on destructive actions like 'reset_node'?). The description is purely a catalog of action names with no disclosure of mutation behavior, persistence, or reversibility for this clearly stateful orchestration tool.

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 uses a compact ledger format that front-loads the core actions and groups the rest into categories. It is reasonably sized given the enormous action surface (50+ enum values). Every line adds action-tier information with no filler. However, it is essentially a long list rather than a structured explanation, slightly reducing readability.

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?

This is a high-complexity tool: 16 parameters, many with nested untyped objects, 50+ enum actions, and no output schema. A careful mapping of which parameters apply to which actions would be necessary for an agent to invoke it correctly. The description only gives terse inline hints in the schema (e.g., 'for launch_node') and the grouped list in the description, leaving significant ambiguity about the dispatch contract, return values, and required parameter combinations.

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?

Schema description coverage is 100%, with every parameter having a description (e.g., 'New node status (for update_node)', 'Override params (for launch_node)'). The descriptions add per-action relevance notes. However, they remain terse and don't explain formats, constraints on nested objects (params, answers, context, metadata are all untyped open objects), or which parameters are required for which actions. Baseline 3 is appropriate given the full coverage.

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 'Onboarding DAG orchestration and setup generation' which identifies the domain, and lists many distinct actions. However, the verb+resource clarity is diffuse because the tool is a multi-action dispatcher with 50+ enum actions; it reads more like a menu than a focused purpose statement. It does help distinguish the tool's scope from siblings like gc_orchestration and gc_workflow, but only at a high level.

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 groups actions into functional categories but provides no guidance on WHEN to use this tool vs alternatives (e.g., when to use gc_onboarding vs gc_workflow, gc_schedule, or gc_directive). It says 'Onboarding DAG orchestration' but never states when onboarding is appropriate versus other workflow/control tools, and there are no explicit exclusions or alternative recommendations.

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