assembly_live_captions_record

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

No annotations exist, so the description carries the full burden and does well: it discloses that the recorder runs as a separate process, that it stops itself when the relay ends, and that recording must precede the relay to be complete. It omits permission requirements, whether an in-progress recording can be stopped or duplicated, and what a status response contains.

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?

Purpose is front-loaded in the first clause, and each following sentence supplies a distinct fact (why pre-record, process lifecycle, parameter sourcing, no-arg behavior). Slightly dense but no redundant restatement of the name.

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 side-effecting tool with no annotations and no output schema, the description covers the critical surprises: a separate process is launched and self-terminates, and the no-arg call returns status. Whats missing is how to inspect or stop an active recording and any permission notes, but nothing essential to a correct first call is absent.

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 100% so the baseline is 3, but the description adds real value by telling the agent that xcode values come from assembly_live, and by clarifying that all=true covers both currently and future relayed broadcasts. That cross-tool sourcing hint is not in the schema.

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?

Opens with a specific verb+resource pair ('의사중계 AI 자막 녹화 시작/상태' – caption recording start/status) that is clearly distinct from the read-only sibling assembly_live_captions. The follow-up sentence explains the resource context (relayed captions) so the agent knows exactly what is being recorded.

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 concrete use condition: the caption server only emits sentences after connection, so recording must be started before/while relaying to capture the full meeting. Also states the zero-argument behavior (status only) and the all=true breadth. It does not explicitly name a sibling alternative to use instead in any case, so it falls short of a 5.

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