get_companion_messages

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

With no annotations, the description carries the burden and discloses the key non-obvious trait: messages arrive automatically on every other tool result, so this tool is normally redundant. It does not disclose that a call consumes/drains the queue by default (the drain parameter implies it), which is a notable side-effect omission.

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, front-loaded with the resource, then the critical caveat and usage conditions. Every clause earns its place with no 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?

For a single-parameter read tool with no output schema and no annotations, the description is nearly complete, covering purpose and routing. The one gap is the consume-on-read default behavior, which it leaves entirely to the schema.

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 100% and the single drain parameter is documented in the schema as "Set false to read without consuming. Default true." The description adds no detail about the drain/consume semantics, so baseline 3 applies.

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 ("Read") and resource ("what the person watching has said while you were working"), making clear this retrieves inbound companion messages. Easily distinguished from siblings like reply_to_companion (outbound) or get_activity_summary.

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?

Explicitly states when NOT to use it ("Messages are ALSO delivered automatically on every other tool result, so you rarely need this") and names the two conditions that justify a call: checking before finishing, or waiting for requested input. This is a textbook when/when-not pairing.

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