create_project

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

No annotations, so description carries burden. It explains it creates a resource and returns an ID, but does not disclose idempotency, error conditions, or permission requirements.

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?

Three short sentences, front-loaded with main purpose, efficient with no wasted words.

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?

Covers both parameters and relationship to submit_plan. Output schema exists so return format is less critical. Missing error cases but adequate for a simple creation tool.

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?

With 0% schema coverage, description adds meaning: goal is the engineering goal, constraints hold non-negotiables like stack, deadline, style rules.

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 registers a new engineering goal and returns a project ID, distinguishing it from siblings like submit_plan and list_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?

Provides clear sequential guidance: call once per goal, then decompose with submit_plan. Does not explicitly state when not to use, but context is sufficient.

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