usage_reconciliation

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

With no annotations, the description carries the full disclosure burden and does so well: it states read-only, that it does not call models, does not collect accounts, does not scan auth, and that missing usage is unknown while evidence-free history is ephemeral and unrecoverable. These limitations go well beyond a bare verb and warn the agent about what this tool will not surface.

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?

Front-loaded with the action and read-only flag, then outputs, then behavioral limits, then parameter caveats. It is dense but every line carries distinct information; nothing is padding.

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?

For a cross-source reconciliation tool with a full output schema present, return values need not be explained, yet the description still enumerates the output buckets (denominators, unregistered threads, ended-without-usage, pricing gaps, truncation). Combined with the behavioral limits and param caveats, an agent has enough 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 coverage is 100%, so a baseline of 3 applies and the schema already documents all five params. The description adds real meaning on top: project_id only filters registered/external associations (journal attribution stays unknown), and since/until must carry a timezone, which is a constraint the schema text only partially conveys.

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?

States a specific verb (reconciliation) plus concrete resources (saved Codex journal, registered agents, external executions) and immediately marks it read-only. It is clear what the tool does, but it never names or contrasts with the very close sibling usage_attribution, so an agent must infer the boundary itself.

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?

'按需' (on-demand) implies this is a deliberately-triggered reconciliation rather than a routine call, which is useful context. However, there is no explicit when-to-use statement, no exclusions, and no routing to alternatives such as usage_attribution, so the agent is left to infer the distinction.

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