raw_publish

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

With no annotations, the description must carry the behavioral load. It usefully discloses the environment-variable gate, the local-transport restriction, and the set of allowed topics, but says nothing about whether payloads bypass validation, what errors occur when the gate is closed, or what the tool does on success.

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 tight sentences: the purpose and the gating prerequisites are both front-loaded, and no sentence is filler. Ideal length for a debug-only tool.

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?

An output schema exists, so return values don't need explaining, and the critical constraints (env var, local transport, allowed topics) are covered. The remaining gap is payload expectations and failure modes, which is minor but noticeable for a tool that accepts arbitrary JSON.

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 coverage is 0%, so the description has to compensate. It does clarify the topic parameter by enumerating the accepted values (cmd, delta, shadow, timeline, testcmd), which the schema lacks, but it gives no guidance on the shape or expectations for the required payload parameter.

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?

Uses a specific verb (publish) and resource (raw JSON payload to a local topic), and frames it precisely as a 'debug escape hatch'. That framing cleanly separates it from the normal command tools in the sibling list (start_clean, set_setting, etc.).

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 'debug escape hatch' label clearly marks this as a last-resort path rather than normal operation, and the required gating (ROOMBA_ALLOW_RAW=1 plus local transport) tells the agent when the tool is even callable. It doesn't explicitly name which sibling to use for normal control instead, so it falls one step short of 5.

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