Precheck a capability call to return metadata and an execution plan without running it, enabling SkillScan checks and human confirmation before real invocation.
能力调用（dry-run 预检）——返回能力元数据与调用计划，不真实执行（SkillScan 拦截 + HITL 确认；真实执行由 Agent runtime 注入 executor）。
| Name | Required | Description | Default |
|---|---|---|---|
| input | No | 调用入参（透传给被调能力） | |
| capability_id | Yes | 能力 ID（必填——先 commons_search 发现） | |
| caller_agent_id | Yes | 调用者 agentId（必填） |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does it well: it discloses dry-run semantics, that nothing is executed, that SkillScan intercepts the call, that HITL confirmation applies, and that real execution is injected by the Agent runtime via an executor. It does not cover error/denial behavior or rate limits, so not a 5.
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?
A single dense sentence that front-loads the most decision-relevant fact (dry-run pre-check, no real execution). Parenthetical detail is compact and earns its place; slightly heavy punctuation but nothing wasted.
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 3-parameter tool with no annotations and no output schema, the description covers the critical behavioral facts an agent needs: it is a dry run, returns metadata/plan, and is gated by SkillScan and HITL. It does not describe the shape of the returned plan, but with no output schema that is a minor gap.
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 description coverage is 100%, so the schema already documents all three parameters, including the pointer to commons_search for capability_id discovery. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.
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+resource: capability invocation performed as a dry-run pre-check that returns capability metadata and an invocation plan without executing. It contrasts itself against real execution handled by the Agent runtime, which meaningfully separates it from the commons_* family.
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 implies this is a pre-check step and the schema notes '先 commons_search 发现' for capability_id, so a discovery-then-invoke flow is hinted at. However, the description itself never states when to use this versus a real invocation path, nor any conditions or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.