compose_pull

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

Beyond the sparse annotations, the description clearly discloses non-raising behavior on non-zero CLI exits, the specific exceptions that still raise (missing compose plugin or timeout), and instructs the agent to inspect `returncode`/`stderr`. It also documents the return dict structure and notes that images are fetched without starting containers, giving a clear behavioral model.

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?

The description is front-loaded with the core purpose, then moves to use cases, exclusions, behavioral caveats, parameter explanations, and return format. Every sentence adds operational value, and the structure makes it easy for an agent to quickly extract invocation requirements without scanning 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?

With no output schema, the description explicitly provides the return dict shape. It covers auth prerequisites, error semantics, parameter defaults, and the relationship to compose_up. For a tool with six parameters and meaningful failure modes, this description is complete enough for an agent to call it correctly and interpret results.

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?

Even though the input schema has 0% property descriptions, the description's Args section fully compensates by explaining all six parameters: project_dir, files, project_name, services, ignore_pull_failures, and timeout_seconds, including defaults, repeatability, behavior when omitted, and the target-host copy nuance. This is exactly what the schema lacks.

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 opens with a specific verb and resource: "Pre-fetch images for a compose project's services without starting them." It immediately distinguishes itself from compose_up by clarifying the pull-only scope, and reinforces the purpose with concrete intents like staging images and verifying accessibility without starting containers.

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?

The description gives explicit when-to-use scenarios (before outage windows, refreshing cache, verifying access) and names the key alternative: `compose_up --pull always`, explaining that compose_pull should be used when the pull step needs to be separated. It also provides the auth prerequisite with `system_login`, leaving little ambiguity about when this tool is appropriate.

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