Gaze and think (flow session)

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses that the flow session is 'CLEAN, isolated', 'runs in the BACKGROUND', 'can read/write files and search the codebase, but has no shell', and explains the wait=true blocking behavior.

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?

The description is dense but every sentence earns its place: it explains what, when, how, and the operational caveats. It is front-loaded with the tool's core purpose and structured to flow from action to use case to background behavior.

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?

Given the tool's complexity (8 parameters, no output schema, no annotations), the description is rich enough to support correct selection and invocation. It covers the workflow, background vs. blocking behavior, and capabilities/restrictions, though it does not specify the exact structure of the returned synthesis.

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. The description adds practical usage context for key parameters (note=, focus=, project=, wait=true), including the pattern of dumping pieces then focusing a session, going beyond raw schema text.

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?

The description clearly states the tool's function: write tangled problem pieces to a board, then launch an isolated flow session to reason about relationships. It distinguishes itself from the sibling scratchbook_gaze_read by explicitly referring to polling/blocking behavior.

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?

It gives explicit guidance: 'Use it when a problem is too tangled to hold in the working session' and explains the workflow with note=..., focus=..., and wait=true. It clearly points to scratchbook_gaze_read for polling, but does not explicitly discuss when not to use it relative to all other sibling tools.

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