record_outcome

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

The description discloses that the tool mutates the persisted record ('updates the persisted decision record in place'), which aligns with readOnlyHint=false. It explicitly states idempotency ('repeat calls with the same value converge'), matching idempotentHint=true. It also explains the return fields, adding value beyond the annotations.

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 efficient and front-loaded: it opens with the core purpose, then covers the computation, persistence behavior, idempotency, and return values in a few sentences. No wasted words; each sentence contributes unique information.

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?

The description covers the essential aspects: purpose, computation, persistence, idempotency, and return fields. It doesn't explicitly mention error conditions or prerequisites (e.g., that decision_id must exist), but these are implied and partly covered by schema. Given the tool's moderate complexity and rich schema/annotations, it's nearly complete.

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 parameters are already documented. The description adds context by explaining the computation of outcome_delta and that actual_outcome is the observed real-world value, clarifying the relationship between actual and expected beyond the schema's basic descriptions. This enriches 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 the tool's function: it records the actual outcome after a decision and computes the delta. It uses a specific verb ('record'), identifies the resource (decision), and explains the computed field. It distinguishes itself from siblings like log_decision (creating) and get_decision (retrieving) by focusing on the feedback loop.

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 when to use the tool ('after a decision was made') and that it's for closing the feedback loop, but it doesn't explicitly contrast with alternatives or state when not to use it. There's no mention of sibling tools like log_decision or execute_decision, leaving the selection reasoning implicit.

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