project_eject

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

Beyond annotations, the description discloses that nothing is copied, moved, or deleted, that writes require confirm and are otherwise refused, and that dryRun returns data.generatedFiles and data.created. This adds real behavioral context for a write tool whose annotations only give generic hints.

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 single dense paragraph, front-loaded with the core action and artifact. Every clause carries information, though it is somewhat long and could be split for scannability.

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?

With no output schema, the description still explains the dryRun return values (data.generatedFiles, data.created) and the write gating, leaving nothing an agent needs in order to call it correctly.

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 coverage is 100%, so the schema already documents all three parameters. The description adds value by tying confirm to the refusal behavior, describing dryRun's return shape, and explaining when projectPath is needed (server not running from project root).

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 specific verb and artifact: 'Write EJECTED.md with `flisk eject --json`', and explains it lists generated Tilt files and how to run the stack with plain Tilt. This is far more specific than the name alone, though it doesn't explicitly contrast itself with siblings like config_regenerate or down.

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?

Clear usage conditions are given: it changes the project and is 'refused unless confirm is true', while dryRun returns the plan without confirm. It tells the agent exactly when the write path is permitted vs the read-only path, though it names no alternative tools.

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