marrow_think

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

With no annotations provided, the description carries the burden. It discloses key behaviors: recording intent, returning a decision_id, auto-committing on previous_outcome, and potential response fields (onboarding_hint, intelligence). It also implies authorization requirements ('authorized governance intelligence'). This is solid but not exhaustive (e.g., error handling or permission details omitted).

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 three sentences long, front-loads the main purpose, and every sentence adds value. It avoids redundant details already in the schema and is well-structured for quick reading.

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 (11 params, nested objects, no output schema), the description covers the essential workflow and return values. It could be more complete with error cases or conditional behaviors, but the schema fills the parameter gaps, making this adequate.

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?

The schema already provides 100% coverage of parameter descriptions, so the baseline is 3. The description adds meaningful context beyond the schema, particularly the 'auto-commit' semantics tied to previous_outcome and the response structure, which helps an agent understand the workflow.

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: 'Record intent and retrieve authorized governance intelligence before acting.' This uses specific verbs (record, retrieve) and specifies the resource (governance intelligence), distinguishing it from sibling tools as a preparatory step for actions.

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?

It provides clear usage context ('before acting') and explains the chaining behavior via 'Pass previous_outcome to auto-commit the last decision and open a new one.' However, it doesn't explicitly contrast with sibling tools or state when not to use it, so it lacks a full when/when-not breakdown.

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