icp_create_project

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

With no annotations provided, the description must disclose behavioral traits, but it only mentions language support and project type without describing side effects, prerequisites, or potential overwrites. There is no indication of what files are generated, whether existing folders are overwritten, or if external tools like dfx are required. This is a significant gap for a scaffolding tool that implicitly modifies the filesystem.

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 concise, with two sentences that front-load the core purpose ('Create a new ICP canister project') and then efficiently convey the key decisions. Every sentence contributes meaningful information, and there is no repetition or fluff.

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 4-parameter tool with no output schema and no annotations, the description covers the essential decision points but omits details about the creation process's outcomes, such as the directory structure or next steps after creation. It is minimally viable but leaves gaps regarding what the user gets after execution, especially given that sibling tools handle subsequent steps like deploying or adding canisters.

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 covers all parameters with descriptions, giving a baseline of 3. The description adds value by explaining the trade-offs between languages (Rust for systems programming vs Motoko for easier syntax) and project types (frontend for HTTP-serving vs backend for stateful API), which helps the agent make more informed choices beyond the raw enum values.

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 creates a new ICP canister project with the verb 'Create' and resource 'ICP canister project'. It goes beyond a tautology by specifying supported languages (Rust, Motoko) and project types (frontend/backend), which helps distinguish it from sibling tools like icp_create_canister that focus on individual canisters rather than entire projects.

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 implicit usage context by explaining when to choose 'frontend' (HTTP-serving) vs 'backend' (stateful API), which guides parameter selection. However, it does not explicitly mention when to use this tool over alternatives such as icp_init_dfx_project or icp_create_frontend, nor does it state any exclusions or prerequisites. This makes the guidance more about parameter semantics than tool selection, but the overall use case is reasonably inferred.

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