Create a new agent

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

With no annotations, the description carries the full burden and does well. It discloses side effects (creates workspace, connects live agent, imports into solution via init/pack/import/clone), prerequisites (auth profile, confirm:true for live changes), and behavior differences based on parameters. This goes beyond the schema and tells the agent what will actually happen.

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 a dense but focused paragraph that front-loads the core action and then walks through modes and parameters. Every sentence adds value, and there is no fluff. It could be slightly restructured for readability, but it's appropriately concise for the complexity.

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?

Given 11 parameters, no output schema, and no annotations, the description is largely complete for the main workflows. It covers the major decision branches (environment, solutionName, authoringMode) and mentions prerequisites. Gaps remain: it doesn't clarify return values, the role of template/schemaName/instructions, or error conditions. Still, for a tool with many options, it provides enough to invoke it correctly in most cases.

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 description adds meaning to key parameters (environment, solutionName, createSolution, authoringMode, confirm) that the schema alone doesn't convey, such as the workflow triggered by solutionName. However, it omits semantics for template, schemaName, and instructions, which are only described in the schema (or not at all). With 73% schema coverage, the description compensates well for the critical parameters but not exhaustively.

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 clearly states the tool's purpose: 'create a new agent workspace on disk' and elaborates on the two main modes (local scaffold vs. live agent). It distinguishes from siblings like cs_update_agent and cs_delete_agent by focusing on creation. The mention of 'pac copilot init' gives a concrete mental model.

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 provides clear conditional usage guidance: without 'environment' it's a local scaffold, with 'environment' it creates a live agent (requiring auth profile and confirm:true), and with 'solutionName' it places the agent in a specific solution. It also contrasts authoringMode options. However, it doesn't explicitly mention when to prefer this over close siblings like cs_clone_agent or cs_init, leaving some ambiguity.

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