start_project

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

Annotations declare destructiveHint=true, readOnlyHint=false, idempotentHint=false. The description adds value by explaining the 'reset' behavior and the gating conditions for multi-agent scenarios (e.g., 'gated until single-agent smokes green unless force_multi=true'). It also clarifies the default ('single-agent default') and the role of force_multi. No contradiction with annotations; the 'reset' aligns with destructive behavior.

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 structured with a bullet list for samples, which improves readability. The main purpose is front-loaded, followed by sample details and then gating rules. It is relatively concise given the information it conveys, though the separate paragraphs could be tightened. It avoids redundancy and wastes little space.

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 that the schema is minimal and annotations are present, the description covers the key behavioral aspects: the reset/start capability, the sample variations, gating for multi-agent goals, and default values. It does not describe return values, but an output schema exists, so that is acceptable. It could be more explicit about what 'coaching checklist' entails or prerequisites like what 'smokes green' means, but these are minor 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 has zero descriptions, so the description must compensate. It does explain the sample parameter extensively (listing values and their UI/scaffold implications) and mentions goal=multi and force_multi. However, it omits an explicit explanation of what 'goal' does beyond the implicit 'single-agent' vs 'multi', and the 'force_multi' parameter is only mentioned in the context of gating. It adds some meaning but not complete coverage for all three parameters.

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 clear action: 'Start or reset first-app coaching checklist'. It defines the verb (start/reset) and resource (coaching checklist), and lists sample variants. However, it does not explicitly differentiate from sibling tools like use_sample or scaffold_app; it mentions them inside the sample descriptions but not as alternative overall purposes. The core purpose is understandable, but the term 'coaching checklist' is somewhat ambiguous without further context.

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 concrete guidance on when to use this tool vs alternatives: it lists sample options and notes that travel and beer can be achieved via use_sample, and api via scaffold_app, implying start_project is the primary entry point. It also explains gating for multi-agent goals (goal=multi or sample=yelp) and the force_multi escape. This is useful, but it does not explicitly state 'use this tool when you want to set up a coaching checklist' or list exclusion criteria beyond the sample paths.

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