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

Annotations only declare readOnlyHint=false, so the description carries the full disclosure burden. It details the rate limit (1 per 5 minutes, 429 with retry hint), accepted registry, plan memory/CPU caps, and re-deployment rules—far beyond annotation coverage.

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 paragraph packs multiple constraints and alternatives without redundancy. The core action is front-loaded, and conditional details (rate limit, plan caps, restrictions) follow logically.

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?

The description covers the action, accepted image source, rate limit, alternative tool, plan caps, and Free plan block. While it does not describe return values (no output schema exists), it notes the rate-limit error scenario, making it complete for correct invocation.

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?

With 0% schema description coverage, the description must clarify parameters. It implies that 'image' is a digest from registry.fiskmas.dev and 'project' is the target project, but it stops short of explicit parameter definitions. Still, the context is sufficient for an agent to infer correct usage.

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 action: 'Pull an image by digest and run one container' with explicit plan caps. It also names the accepted registry, distinguishing it from sibling tools like start_project and restart_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?

Explicitly directs the agent to use restart_project for transient crashes, noting it does not count against the rate limit. It also clarifies when re-deploying is allowed and that starting a second project on Free is blocked.

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