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

Annotations flag the mutation profile, and the description adds substantive behavior: the `needs_user` status pauses only this call while the session stays open, the handoff URL is surfaced, sessions self-close after idle minutes, and the exact response shape `{ sessionId, ok, status, result, logs, error?, code? }` is disclosed. This is well beyond what annotations provide.

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 purpose and the `run` contrast before mechanics. Dense but every sentence carries information; slightly long, though the length is justified by the stateful session protocol it must explain.

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?

No output schema exists, so the description carries the return contract itself and does so completely, including status values and the optional error/code fields. For a stateful, destructive, open-world tool, all the information needed to call it correctly across multiple turns is present.

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 meaning: `path` is the dotted path a script writes after `bowmark.` with a concrete example, `args` are positional, and `sessionId` is omitted on the first call so a session opens and its id is returned. The `get_library` lookup instruction is extra semantic guidance not present 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?

States a specific verb+resource ('Runs ONE library function in a Bowmark session') and immediately distinguishes it from the sibling `run` by explaining that run starts a fresh browser per call. An agent can tell them apart without opening either 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?

Explicit when-to-use ('a flow that needs several calls in the SAME browser'), when-not ('run cannot do these'), and the lifecycle rule: omit sessionId on the first call, pass it on every later call, and call `session_close` when done. It also routes the agent to `get_library` before calling.

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