kingdee_query_report

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

Annotations already mark it read-only, idempotent and non-destructive, and the description adds substantial operational context beyond that: the formid-must-be-a-separate-form-field root cause, the totalWidth/PadLeft crash when FBALANCELEVEL=0 without FSHOWFULLNAME, the StartRow/Limit vs PageIndex/PageSize distinction, and the fact that a 0-row result is normal rather than a failure. These are non-obvious failure modes an agent could not infer elsewhere.

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 verb, endpoint and the key constraint, then structured into endpoint notes, verified formIds, and a worked model example. It loses a point because the full example model payload is duplicated almost verbatim inside the schema's data description, so some sentences do not earn their place twice.

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 complex, free-form JSON-passthrough report API with one opaque parameter, the description supplies the endpoint contract, verified ids, a working payload, the pagination convention and the known server-side errors. An output schema exists, so the brief return-value note is sufficient.

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?

With the reported 0% schema coverage on the declared parameter, the description carries the full burden and does so: it spells out the model structure (FieldKeys / Model / StartRow / Limit), names the filter field families (FACCTBOOKID.FNumber, FSTARTYEAR/FSTARTPERIOD/FENDYEAR/FENDPERIOD, FBALANCELEVEL), and annotates the field-name and level pitfalls. It also documents the form_id enumeration, including the no-RPT_-prefix exception.

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 and resource: queries any GL/financial report via GetSysReportData, and names the exact endpoint. It explicitly contrasts itself with document query (ExecuteBillQuery) and with the unusable KDSReportAPIService, so an agent can separate it from kingdee_query_bills and friends without opening a schema.

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?

Gives concrete when-to-use context (report queries vs. document queries), lists the two verified formIds with the exact selectors, and warns that most other report formIds must be verified in BOS/ApiDoc first. It falls just short of a 5 because it does not name the sibling tool to use for the document-query case, referencing only the underlying ExecuteBillQuery API.

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