cf_start

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

With no annotations, the description carries the full behavioral burden but says nothing about whether the operation is asynchronous, whether it waits for the instance to become healthy, required permissions/targeting, or what happens if the app is already running.

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?

A single compact phrase with zero filler and the action front-loaded. It is efficient, though arguably under-specified rather than optimally sized.

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 simple one-parameter mutation with no output schema, the essentials (what it acts on) are present, but the result state, targeting requirement, and distinction from cf_restart are missing, leaving the agent to infer the mutation's outcome.

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?

One parameter at 100% schema description coverage, so the schema already explains appName. The description adds no format details (e.g., whether appName is case-sensitive or must exist in the current target), so the baseline 3 applies.

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 ('Start a stopped application'), and the qualifier 'stopped' usefully narrows scope versus the sibling cf_restart. However, it does not explicitly differentiate itself from cf_restart/cf_restage, which also bring an app up.

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?

Usage is only implied by the word 'stopped' – an agent can infer this applies to a non-running app, but there is no explicit when-to-use guidance, no statement of prerequisites (e.g., must be targeted to a space), and no routing to cf_restart as the alternative.

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