project_init

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the safety profile is partly covered. The description adds real value beyond that: it discloses that an existing project's project.json is never overwritten and that generated files are refreshed, and it states the return value is the command's text output. It does not mention permissions, failure modes, or the cost of cloning.

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?

Dense but front-loaded: the creation path comes first, then the template branch, then the in-project refresh caveat, then the return value. It is a single long, slightly run-on construction with heavy parenthetical nesting, which costs some readability, but no sentence is wasted.

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, zero-required mutation tool with no output schema, the description covers all three execution modes, the two-step template workflow, the overwrite guarantee, and what is returned. It is nearly complete; a hint about prerequisites (auth, existing directory errors) or how refreshes interact with config_regenerate is the only meaningful gap.

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 baseline is 3. The description still adds meaning: projectPath defaults to the server's directory and must be an existing directory, path is template-only and relative to projectPath or absolute, and the template plus second-call workflow is explained. Only agentSkills is left entirely to the schema.

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?

States a specific verb and resource ('Create a Flisk project') and enumerates three distinct modes: blank creation, template clone, and refresh of an existing project. It is clear about what gets written (.flisk/project.json plus generated files), but never names or contrasts the closest siblings (project_import, project_eject, config_regenerate), so differentiation is left to inference.

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?

Gives concrete usage conditions: use template to clone a starter, call again with projectPath set to the clone to configure it, and note that inside an existing project the tool refreshes instead of creating. That covers sequencing and the main when-to-use branches. It stops short of explicitly excluding alternatives or stating when a different tool (e.g. project_import) should be used instead.

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