confirm_ontology

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

With no annotations, the description carries the full disclosure burden, and it does state the key behavioral traits: the submitted decisions become this file's reference ontology and are immediately compared against it. That tells the agent the call mutates persistent reference state and triggers a comparison result. It omits overwrite/replace semantics for a pre-existing reference ontology and any validation or failure behavior.

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 sentences with the effect stated first and the structural example second, so the payload contract does not bury the purpose. The inline JSON example is dense but each part earns its place as the only documentation of the nested shape. Minor cost: the mixed prose/JSON sentence is harder to scan than a separated format block.

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 mutation tool with a nested payload and no output schema, the description covers the write side well but says nothing about what the immediate comparison returns, which an agent needs since no output schema exists. Overwrite behavior on repeated confirmation is likewise unaddressed. Adequate but with a clear gap on the return side.

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%, but the schema for `decisions` explicitly defers to the description ('形状见上面'), so the description is the only place the nested verdict vocabulary ("ok"|"wrong"), the optional rename label, and the `added` list for missed objects are defined. That is substantive meaning the schema does not supply, including an enum-like value set the schema lacks.

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 states a specific verb and resource: persisting the human's item-by-item verdicts on the ontology, making them the file's reference ontology and comparing immediately. That is more than a restatement of the name and conveys the effect. It stops short of naming the closest sibling (confirm_derived) or clarifying how it differs from compare_reference, which it partly overlaps with.

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?

Usage is implied by '人的逐项判断' (the human's per-item judgments) and the required saved_as coming from list_runs or build_ontology, so an agent can infer this is the confirmation step after a run. There is no explicit when-to-use / when-not statement and no distinction from confirm_derived or compare_reference, leaving the choice partly to inference.

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