inject_signal

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

No annotations exist, so the description must disclose side effects and it does: it states quiet-state restoration (0.0 signal) automatically occurs, notes the 1-loop RealtimeBuffer delay, and explains timestamp filling/preservation behavior. This is high-value behavioral context.

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 and then organized into useful caveats, though it is fairly long and includes an awkward nested parentheses structure. Every section adds relevant information.

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 an output schema exists, return values need not be described. The description covers the crucial injection-point pitfall, automatic restoration, and timestamp behavior, making it strong for the intended use case. It remains incomplete for general use because key parameters like `force` and `confirm_token` are not explained, and the waveform set is partially described.

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 0%, so the description bears the burden. It adds meaning for `topic`/`field`/`extra_fields` via the GimbalCmd example and mode constants, but does not document `force`, `dry_run`, `amplitude`, `frequency`, `duration_sec`, `publish_rate_hz`, or `confirm_token`. It also says 'step or sinusoidal' while the schema also supports square and triangle waveforms, a notable gap.

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 opens with a clear verb and resource: 'Inject a step or sinusoidal excitation signal into a command topic.' It further differentiates the tool by warning against injecting into PID-computed output topics, clarifying its role relative to signal injection.

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?

Provides explicit placement guidance: inject at controller INPUT with a concrete example topic/message, and explicitly says NOT to use */controllers/<axis>/command (std_msgs/Float64) since that is PID output. It does not mention alternative sibling tools or when to prefer step vs. sine/square/triangle, so it misses full alternative coverage.

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