report_returns

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

Beyond annotations (readOnlyHint, idempotentHint, destructiveHint), the description adds critical behavioral details: 'O(1) per return' and 'the raw returns are not stored.' This helps the agent understand side effects and performance. It does not contradict 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 two sentences that front-load purpose, then provide essential behavioral context (O(1), not stored), then usage timing. Every sentence adds value without redundancy.

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 is sufficient for an agent to use the tool correctly: it explains what happens, what is returned conceptually (verdict), and when to call. It lacks an explanation of what HELD/DECAYED/BROKEN mean, but that is domain knowledge likely covered by other tools. No output schema exists, but the description names the verdict types.

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 100%, so the baseline is 3. The description repeats the high-level meaning of 'new_returns' ('new live returns') and 'commitment' but adds no syntax or format details. The schema already handles this adequately.

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 states a specific action ('Fold new live returns into a commitment') and a specific outcome ('get the current HELD / DECAYED / BROKEN verdict'). This clearly distinguishes it from sibling tools like open_commitment (which creates) or commitment_status (which reads). The title annotation reinforces this.

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?

'Call it whenever you have new live data — daily, weekly, whenever' explicitly states when to use the tool. It mentions the trigger condition (new live data) but does not explicitly name alternatives or exclusions, which would merit a 5.

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