trw_probe

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

No annotations are provided, so the description carries the full burden. It details the sandbox environment (SAFE-001, subprocess, seccomp, no-network default), resource bounds (timeout_s, memory_mb), return type (ProbeResult with verdict), budget enforcement, and caching. It does not mention potential side effects or cleanup, which prevents a perfect score.

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 a single, well-structured paragraph. It starts with the primary purpose, then usage context, execution details, and return value. Information is front-loaded. Some phrasing could be more concise (e.g., 'a typed...comes back'), but overall it is efficient.

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 8 parameters (2 required), 0% schema coverage, and an output schema (exists but not detailed), the description covers main usage, sandbox, return type, budget errors, and caching. It mentions error returns but lacks specifics on error handling or edge cases. Overall, it is fairly complete for a probe tool.

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 mentions key parameters (command, timeout_s, memory_mb, etc.) but does not explain each in detail or provide format constraints. For example, it does not clarify the 'run_id' parameter's purpose or the valid values for 'planning_mode'. While context is given, precise semantics are lacking.

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 purpose: 'Run a bounded, sandboxed experiment to resolve a disputed plan assumption.' It specifies the action (run experiment) and the resource (disputed assumption), and distinguishes from sibling tools by referencing the PLAN phase and plan branch disagreements.

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?

Explicitly states when to use the tool: 'during the PLAN phase, two plan branches disagree on a load-bearing, empirically resolvable claim a rubric cannot adjudicate.' Provides an example. However, it does not specify when not to use it or suggest alternative tools, which slightly lowers the score.

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