enable_afg

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

With no annotations, the description carries the full burden and exceeds it. It discloses the dangerous nature, the two-step confirmation flow (first call returns token, second call consumes it), token properties (channel-bound, single-use, expires), and the critical safety requirement to never self-confirm or drive live circuits. It also states the exact return shape ('settings with output true'). This is thorough behavioral disclosure well beyond the schema.

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?

Every sentence earns its place. The dangerous warning is front-loaded, followed by the two-step flow, then required safety checks, and finally return behavior and pointer to disable_afg. There is no redundant or vague wording; the structure guides the agent from danger identification to safe execution.

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 (dangerous action, two-step confirmation, no output schema, no annotations), the description is remarkably complete. It covers prerequisites, the exact calling sequence, safety constraints, token lifetime, and return value. It even tells the agent what to show the human user. Any missing edge cases (e.g., invalid token error) are minor given the strong procedural guidance.

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 0%, so the description must compensate. It thoroughly explains confirm_token: it comes from the first call, is required for the second, is single-use and expires. Channel is less explicit; the description references 'this channel' in the token binding but doesn't directly explain the parameter's valid values or meaning. Still, the description adds substantial semantic value for the more complex parameter, earning a 4 rather than a 3.

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?

Purpose is explicitly stated with a specific verb and resource: 'turn the function generator output on (a real signal starts coming out).' It distinguishes itself from disable_afg by explicitly naming it as the complementary off-switch, and from get_afg_state as the read-before-act tool. No ambiguity about what this tool does.

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 states it is 'the only tool that makes the instrument drive a signal,' which clearly establishes when to use it versus any sibling. It also prescribes a specific workflow: read get_afg_state first, show the user, ask about safety, then confirm. It names disable_afg as the tool for turning the output off, giving clear alternatives and conditions.

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