导出经营证据

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the fact that it produces an evidence structure for evidence_add, which clarifies the output's purpose but does not disclose any other behavioral traits like side effects, validation rules, or error conditions. Given annotations, this is adequate but not enriched.

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 description is a single, concise sentence that front-loads the core purpose. It avoids fluff and is easily parsed. However, it may be too terse given the complexity, but as a structural evaluation, it is efficient.

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?

The tool has five required parameters, a nested object, no output schema, and zero schema coverage in the description. The description provides no guidance on how to construct the evidence structure, what each parameter represents, or any constraints or examples. This is completely inadequate for an agent to call it correctly.

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 0%, meaning the description must explain the parameters, but it does not. It only mentions 'analysis result' generically without clarifying what project_id, analysis_type, summary, analysis, or source_report_ids mean, or how they map to the evidence structure. This is a critical gap for a tool with five required parameters, including a nested object.

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 ('wrap') and resource ('analysis result' into an 'evidence structure'), and names the downstream consumer (orange_island_core evidence_add). This clearly differentiates it from sibling analysis/report tools, which are about generating or retrieving data rather than packaging it for another system.

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 a post-processing role (wrapping an analysis result for a specific target), but does not explicitly state when to use this tool versus alternatives, nor any exclusions. The mention of evidence_add gives context, but an agent is left to infer that this is the final step before handoff.

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