compass_check

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

With no annotations, the description carries the full burden. It explains the tool's behavior: evaluates against governance heuristics, returns verdicts with rationale, and details the effect of the `stakes` and `with_simulation` parameters. Missing details on error handling or edge cases, but overall transparent for the intended use.

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 concise (5 sentences), front-loaded with the core purpose, and structured logically: first states what it is, then explains verdicts, then usage, then parameter details. No redundant sentences.

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 (4 parameters, no output schema), the description adequately covers purpose, verdicts, parameter behavior, and usage context. It could benefit from describing the output structure more explicitly, but the mention of 'rationale and suggested verifications' suffices for an agent to understand the return value.

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 100%, so baseline is 3. The description adds value beyond the schema examples for `action` (e.g., 'git push to main'), clarifies `stakes` behavior (critical defaults to PAUSE), and explains the `with_simulation` parameter in depth (Monte Carlo simulator, NetworkX import). This extra context improves parameter understanding.

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 it is a runtime self-check before high-stakes actions, with a specific verb (evaluates, returns) and resource (governance heuristics). It distinguishes itself from sibling tools by providing concrete examples of when to call it (git pushes, deletes, publishes, deploys) and explicitly listing the three possible verdicts.

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 (before irreversible actions) and explains the meaning of each return verdict (PAUSE, WITNESS, PROCEED). It does not explicitly mention alternatives or when not to use, but the context from the sibling list and the specificity of the use cases provides sufficient guidance for an agent.

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