compose_down

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

Goes well beyond the annotations by naming what is removed (containers), what failure looks like (bind mounts in use), and how to recover. The annotations declare destructiveHint=false, and while removal is recoverable via compose_up, the description never warns that volumes_prune=True deletes persistent volume data — the one truly irreversible action here is undisclosed.

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?

Front-loaded with the core action, then recovery, then return format and examples — a sensible priority order with no filler prose. The return-format block is partly duplicated by the existing output schema, so a little trimming is possible.

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?

Safety-relevant context (recovery on failure) is present and the output shape is covered, but for a zero-required-parameter, 0%-schema-coverage mutation tool it leaves meaningful gaps: the meaning of remove_orphans, the timeout behavior, and the data-loss implications of volumes_prune.

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 description coverage is 0% across four parameters, so the description must compensate and largely does not: 'timeout' (300s) and 'remove_orphans' (default true, which silently deletes non-compose containers) are never mentioned, and path/volumes_prune appear only as bare example arguments with no explanation of effect or data risk.

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 pair and resource ('Stop and remove Compose containers') and anchors it to the canonical CLI equivalent ('docker compose down'), which lets an agent distinguish it from compose_up, compose_restart, and compose_ps without opening a schema.

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?

Gives a recovery path for failure ('stop consumers or use docker CLI for force removal'), which is genuine when-it-fails guidance. But it never says when to prefer compose_down over compose_restart (a sibling that also stops containers) or what happens to running services not managed by the compose file.

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