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

Goes well beyond the readOnlyHint=false annotation by disclosing that it recreates the pod, re-runs the injected-DB resolver gate and storage probes, waits for readiness, returns named errors on failure, is not rate-limited, and that a plain retry clears transient DNS drops. This is rich operational context an agent can't infer from annotations.

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 tightly packed sentences, front-loaded with the core action, followed by behavioral detail and the redeploy caveat. Every sentence earns its place 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?

Behavioral and failure-mode context is complete for a restart tool with no output schema, including error naming and retry guidance. Minor gap: the sole parameter's semantics (which project, how identified) are under-described given 0% schema coverage.

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 0% for the single 'project' parameter, so the description must carry the burden. It says 'a running project's container' implying the project identifies the target, but adds no format, identifier style, or default (required count is 0, yet no default is described). Baseline-minus gap due to 0% coverage.

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?

State a specific verb and resource ('Restart a running project's container') and explicitly distinguishes itself from sibling redeploy/deploy operations. The scope ('a running project') clearly differentiates it from start_project and deploy_project.

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?

Clearly implies when to use this (restart a running project) and explicitly states when NOT to use it for env changes ('Env changes are NOT picked up by a restart - redeploy instead'). It names the alternative (redeploy) but doesn't map it directly to the sibling deploy_project by name, leaving a small gap.

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