compose_list

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

Annotations already declare readOnlyHint=true and destructiveHint=false, reducing the burden. The description adds useful behavioral context: it raises RuntimeError on CLI failure and returns parsed list output from `--format json`. This goes beyond the annotations without contradicting them.

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 compact and well-organized: a one-line purpose, a clarifying sibling contrast, error behavior, then args/returns. Every sentence adds value without redundancy.

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 one optional parameter, no output schema, and read-only annotations, the description covers all essential aspects: purpose, scope, parameter, return format, and error behavior. It is a complete, self-contained description for a simple list tool.

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?

The only parameter `all` is described as 'Include stopped projects', directly explaining its meaning beyond the schema. Given schema description coverage is 0%, this full compensation is essential and well done.

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 clearly states the tool lists compose projects known to the daemon, with the specific scope 'across all directories'. It further distinguishes itself from sibling `compose_ps` by explaining the project-level view vs. container-level view.

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?

It explicitly contrasts with `compose_ps` (which lists containers of a single project), signaling when to choose this tool over that alternative. The context of listing across all directories and including stopped projects via the `all` arg provides clear usage guidance.

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