record_decision

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

The description reveals key behaviors: the record is immutably sealed in S3 Object Lock for 7 years, queryable for lifetime, and that raw inputs are hashed locally before transit (the raw text never leaves the server). It also warns that ai_decision_output should not contain raw PII.

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?

Three concise sentences cover purpose, key features, and usage guidance. No wasted words; every sentence adds value. Front-loaded with the main action.

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 no annotations and no output schema, the description provides substantial context: data handling, retention, compliance, and typical use cases. It does not explicitly describe the return value, but the focus on audit trail and immutability implies a confirmation or ID. Overall, nearly complete for the tool's complexity.

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 already covers all parameters with detailed descriptions. The main description adds context like 'hashed locally' for raw inputs and mentions EU AI Act relevance for human_in_loop, which goes beyond the schema. Baseline 3 with extra value gives a 4.

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 verb (Record) and resource (AI decision to the audit ledger), and it lists what is stored. It also implicitly distinguishes from siblings list_decisions and verify_decision by focusing on writing rather than reading or verifying.

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 says when to use: immediately after any AI decision that may need auditing (credit, hiring, etc.). Does not mention when not to use or alternatives, but the sibling tools are for different purposes, so guidance is clear enough.

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