sx_push

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

With no annotations, the description carries the behavioral burden. It discloses that the operation returns a target data packet requiring pushPar on save, and that it is rejected by a read-only guard by default. This is important context, though it omits permission requirements and broader side effects.

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?

Two concise sentences: first states purpose and a real-world example, second covers parameter selection and behavioral caveats. Information is front-loaded and every sentence earns its place with no 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 covers the essential aspects: operation type, two invocation modes, and the required pushPar feedback, plus the read-only guard. Given no output schema, it does mention the returned data packet. Missing error handling or detailed response format, but not critical for a knowledgeable agent.

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 0%, so the description must explain parameters. It clearly explains the roles of bill_ids, entry_ids, and src_entry_mark. src_form_id and dest_form_id are self-evident from their names, so the description adds meaningful context for the ambiguous parameters even if not all are enumerated.

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 pushes a source document to a destination form (e.g., loan to reimbursement), using the explicit verb '下推' (push). It distinguishes from sibling tools like sx_submit or sx_audit by specifying this is an official push operation, and provides a concrete example.

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 gives explicit parameter selection rules: use bill_ids for bill-level push, entry_ids plus src_entry_mark for entry-level push. It also flags the read-only guard default rejection, which is crucial for correct invocation. This is clear, actionable guidance that prevents misuse.

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