Native API discovery and calls / 原生 API 检索与调用

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

Annotations declare destructive/open-world/non-idempotent, and the description goes well beyond them: model-state guards persist, the selected method may overwrite/delete or trigger external effects, unsupported routes and failed calls are errors, and a lost write reply has unknown outcome with no automatic rollback, so objects must be inspected before retry. Nested branch docs add permission tiers, update_model commit semantics, and cascade defaults for removals. No contradiction with destructiveHint=true.

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 top-level description is front-loaded — purpose first, workflow second, hazard warning last — and every sentence carries a constraint. It is dense but justified for a destructive escape hatch; the very large nested branch documentation (

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?

With an output schema present, return-value documentation is unnecessary, and safety hints are already in annotations, yet the description still covers auth/permission implications, state guards, forbidden methods, no-rollback retry policy, and the discovery prerequisite. Nothing an agent needs before invoking a destructive native call is missing.

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 baseline is 3; the description lifts it by saying kwargs are native backend parameters with method-specific units, that field names must not be translated, that signatures must not be invented or units inferred from another endpoint, and that operation distinguishes inspection from execution. These are genuinely useful usage constraints, though they are meta-rules rather than per-parameter meaning.

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 two-part verb+resource: discover installed qtmodel methods and call a native API, explicitly scoped to cases where "a dedicated domain operation does not expose the required feature." It separates itself from curated siblings and names the two sub-operations (list_qtmodel_api, call_qtmodel_api) plus the diagnostic sibling (inspect_bridge), so an agent can route 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 an explicit when-to-use condition (curated tool lacks the feature), an explicit preference/exclusion ("Prefer the relevant domain operation for supported tasks because it supplies typed arguments and engineering guidance"), a mandated two-step workflow, and a redirect for a related need (inspect_bridge for connection diagnostics). The nested branch docs reinforce this with a list of forbidden methods and their designated replacements.

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