bowire.record.start

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

No annotations are provided, so the description carries the full burden and does so well: it discloses the two-phase pending/confirmation handshake, that capture-mode invokes buffer until stop, the return shape of the first call, and the 409-equivalent failure when a session is already open. It omits auth requirements, rate limits, and what happens to an abandoned session, which keeps it from a 5.

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 layers lifecycle, protocol, and failure mode in a logical order with no filler sentences. The issue-reference parenthetical ("#285") is noise an agent doesn't need, and the sentence is dense, but nothing else is wasted.

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?

With no output schema, the description compensates by naming the first call's return fields ({ pending, confirmationToken, plan }) and the failure behavior, and it covers the mode and lifecycle context an agent needs. For a six-parameter session-control tool, nothing essential is missing.

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%, so the baseline is 3, but the description adds genuine meaning by explaining what each mode actually does (record live invokes vs. proxied flows vs. drive replay) rather than just listing enum-like values. It stays silent on name/workspaceId/recordingId semantics beyond what the schema already states.

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 ("Begin a new server-side recording") and immediately bounds the operation by naming bowire.record.stop as the terminating counterpart. An agent can distinguish this from siblings like record.replay and record.list without opening the 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?

Explains the three modes (capture/proxy/replay) and the two-step confirmation flow with an explicit re-invoke condition, plus the one-active-session-per-process precondition. It does not explicitly route the agent between this tool and the sibling bowire.record.replay, so it falls just short of full when-vs-alternative guidance.

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