predictive_safety_check

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

With no annotations, the description carries the full transparency burden. It discloses that it evaluates, auto-corrects, and returns proof, but it does not clarify whether it mutates system state or only returns corrected values, what happens when the input is safe, or any side effects. 'Auto-correcting' is ambiguous—whether it actually applies the correction or just suggests it—which is a significant gap for a tool that might affect the robot.

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 core sentence is information-dense and to the point, covering evaluation, auto-correction, and proof output. However, the '[WORLD-FIRST]' prefix is noise and does not earn its place, and there is no structural breakdown (e.g., separate sections for behavior and parameters). It is concise but not perfectly clean.

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 complex tool with no output schema and no annotations. The description mentions returning mathematical proof but does not specify the return structure (e.g., fields like safe, corrected_value, proof), nor does it describe error cases, limits, or preconditions. Given the tool's potential to affect commands, the description is insufficient for an agent to use it correctly without guessing.

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 baseline is 3. The description adds some context by mentioning 'parameter or velocity commands' and 'auto-correcting', which aligns with the parameters, but it does not add substantial meaning beyond the schema. The parameter descriptions themselves are minimal and the tool provides no extra detail about required value formats or constraints.

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 uses a specific verb ('evaluates') and identifies the resource ('proposed parameter or velocity commands') and the criterion ('against dynamic stability bounds'). It also mentions auto-correction and returning proof, clearly distinguishing this from sibling tools like publish_topic or set_parameter, which execute commands directly.

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 implies its usage for safety-checking proposed commands ('proposed parameter or velocity commands', 'unsafe LLM inputs') but does not explicitly state when to use it instead of directly calling publish_topic or set_parameter, nor does it mention exclusions or alternatives. This leaves the agent to infer the appropriate context.

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