Model records and geometry checks / 模型数据与几何检查

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the bar is lower, and the description still adds real behavioral content: calls neither solve nor make the model editable, generic getters slice locally while native queries page on the bridge, selectors must be preserved between pages, and 'empty data is not proof of a missing entity when a filter or unavailable backend is involved.' It stops short of covering failure modes or auth requirements in depth.

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 purpose, then operations, then alternatives, then routing mechanics — a logical progression. It is long and dense, but the length is justified by ten discriminated branches; a few clauses (e.g., the bilingual parenthetical) are redundant but not wasteful.

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 ten-branch dispatcher with rich nested schemas and an output schema, the description supplies the routing model, sibling disambiguation, and empty-result/pagination caveats, so the agent needn't be told about return values. Coverage is strong; per-branch units and edge constraints are left to the nested schemas, which is appropriate.

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 100% schema coverage and only one top-level parameter (request), the baseline is 3; the description earns extra by explaining the dispatch contract: 'request.operation selects one schema branch' and that query_model_data's typed request remains nested, with a concrete example. It clarifies that IDs/names refer to the current model.

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 opening sentence states a specific verb+resource+constraint ('Read saved model definitions, locate entities or inspect model geometry without changing it'), then enumerates each of the ten operation branches (get_model_info, get_model_data, query_model_data, find_entities, list_group_members, tendon/transversal/international getters, calc_section_property, validate_model) with what each does. An agent can identify this tool's scope without opening the 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?

It explicitly routes the agent away to alternatives by condition: 'Use inspect_bridge for connection and permission diagnostics, query_results for solved responses, and manage_checks for the current concrete-checking context.' It also sub-differentiates within the tool, noting validate_model checks connectivity/definition consistency 'not structural adequacy' and that calc_section_property evaluates candidate geometry without storing it.

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