start_monitor

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

With no annotations provided, the description carries the full burden. It clearly discloses the security posture: bound to 127.0.0.1 only, requires a random per-monitor token, and unencrypted. It describes what the page renders (rolling traces, event markers, band power, per-channel quality) and the control-button behaviors. It doesn't explicitly state the return value format, but an output schema exists. Solid coverage for an unannotated tool.

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 well-structured and front-loaded: first sentence states the core action, then a paragraph on rendering, then the allow_control distinction, then security. Every sentence earns its place and there is no fluff or repetition.

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?

This is a moderately complex tool with 5 params and an output schema. The description covers the use case, the difference between control and read-only modes, the security posture, and all parameter semantics are already in the schema. The network-binding caveat is an important operational detail an agent would need. This is complete for an agent to invoke correctly.

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 schema already documents all 5 parameters well (port, refresh_ms, session_id, window_sec, allow_control all have clear descriptions). The tool description adds incremental value by explaining the behavioral meaning of allow_control (enables transport buttons) and noting window_sec is adjustable in-page. This matches the baseline-3 expectation for high schema coverage.

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 states a specific verb+resource ('Open a live browser view of a running session and return its URL') and clearly distinguishes itself from static plot alternatives ('a static plot cannot answer whether the signal is good *now*'). It also differentiates this monitor tool from related sibling tools like plot_stream, start_replay, and inspect_recording.

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?

The description explicitly states when to use this tool ('This is the tool for let me watch the recording'), gives a concrete use case for when to use allow_control=false ('showing the screen to someone who should not be able to alter the run'), and contrasts it against static plots. It also warns against tunneling due to lack of encryption.

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