up

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

Annotations already declare readOnly=false, destructive=false, and openWorld=false. The description adds real value beyond this: it explains the non-blocking/detached semantics, where readiness must be checked, and the concrete fail-fast conditions including the already-running conflict (with `force` as the replacement escape hatch). Return shape is left implicit, which keeps it from a 5.

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 the primary action and its non-blocking contract, followed by the readiness-polling instruction and failure conditions. Every sentence carries distinct information with no filler.

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 no output schema, the description usefully redirects the agent to `status` for readiness and spells out fast-failure conditions, which is the critical context for a start tool. Minor gaps remain around what the returned handle/response contains, but the essential call-and-poll workflow is covered.

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 description coverage is 100%, so the schema already documents only/force/stack/dryRun/projectPath/waitSeconds in detail. The description only echoes that projectPath is optional and that partial starts are possible, adding little syntax or behavioral detail beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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+resource ('Start the stack (or part of it)') plus the key behavioral distinction that it runs detached and returns without waiting for readiness. It names the sibling tool to poll for readiness, which helps separate it from read-only siblings like status.

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 clear operational context: use this to start, then poll `status` for data.tilt.readiness.ready rather than expecting this call to block. It also lists when this fails fast (unknown service, unsupported host, or Tilt already running), which frames the preconditions. It does not explicitly contrast against siblings like runtime_check or resource_restart.

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