Record Verified Task Outcome

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

The annotation destructiveHint=true already signals a write operation. The description adds valuable behavioral context: idempotency (safe retries) and the rule that a completed response without evidence is recorded as not working. This goes beyond the annotation and clarifies side effects without contradiction.

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 two sentences long, front-loaded with the verb and core purpose, and contains no fluff. The second sentence adds a critical behavioral rule that earns its place.

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?

Despite being concise, the tool is complex (16 parameters, 7 required, nested objects). The description provides only a high-level summary and one edge-case rule. It does not explain required fields, status semantics, or how the components interrelate, leaving a significant gap for an agent to invoke it correctly.

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 only lists high-level categories (verification, toolCalls, policy, efficiency, businessOutcome) that map to some nested objects, but it omits essential fields like taskId, goal, and status, and provides no structural or format guidance for the 16 parameters. This is insufficient for a tool with zero parameter descriptions in the schema.

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 uses a specific verb 'Record' with a clear resource 'task-level outcome' and enumerates the included data categories (verification evidence, tool correctness, policy behavior, latency, cost, business KPI movement). This clearly distinguishes it from sibling read tools like get_task_outcomes.

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 the tool is for recording task outcomes after verification, and the idempotency note suggests retry safety. However, it does not explicitly contrast with alternatives or state when not to use it, though the context is clear enough for an agent to infer its primary use.

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