raw_command

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

No annotations are provided, so the description carries the full behavioral burden, and for an arbitrary-command escape hatch that burden is heavy. It does not say whether commands mutate the project, whether dry_run is the safe path, what auth/permissions are needed, or what happens when an unknown type is sent. The 'escape hatch' framing implies risk but discloses none of it.

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?

Two sentences, zero filler, and the critical framing ('Escape hatch') is front-loaded so the agent understands the tool's role immediately. The reference pointer is packed into the same sentence rather than a separate paragraph.

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?

For an open-ended, unannotated command-execution tool with no output schema and a nested payload, the description is thin — it says nothing about mutation risk, return shape, or failure modes. The pointer to bridge/command_schema.md partially compensates by acknowledging the command space is defined elsewhere, which keeps it from being inadequate.

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 only 25% (dry_run alone is documented), so the description must compensate. It names the two core inputs (type + payload) and points to bridge/command_schema.md for the full command reference, which adds real value. However timeout_ms is never mentioned and the payload's nested structure is left entirely to the external doc.

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 names a concrete action and resource — 'send any bridge command by type + payload' — and explicitly frames itself as the escape hatch. The line 'Use when no dedicated tool covers it' clearly differentiates it from the long list of specific siblings. The only mild vagueness is what a 'bridge command' actually is, which is deferred to an external reference.

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 gives a direct when-to-use rule: only when no dedicated tool covers the task. That is exactly the routing condition an agent needs to avoid reaching for this over a specialized tool like transport or fx. It stops short of stating when NOT to use it (e.g., never for known operations) or any fallback behavior on failure.

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