evidence_pack

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

No annotations are provided, so the description bears the full burden of behavioral disclosure. It describes what the tool collects and produces (a JSON file) but does not disclose side effects, required permissions, rate limits, or whether the tool modifies browser state or existing data. Key behavioral traits (e.g., if it triggers side effects, if it is safe to call repeatedly) are missing.

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 long sentence that lists many components. It is front-loaded with the core purpose, but the enumeration of artifacts makes it dense and harder to parse quickly. It could be restructured into bullet points or a clearer summary while remaining concise.

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 19 parameters, no output schema, and no annotations. The description explains what the output is (a JSON file) but does not describe its structure, how the parameters interact, typical usage patterns, or prerequisites (e.g., prior browser steps). For a complex data-gathering tool, this level of completeness is insufficient for an agent to confidently invoke it.

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 baseline is 3. The description does not add meaning beyond what the schema already provides for each parameter; it simply summarizes the tool's overall behavior. Parameters like 'har', 'screenshot', 'snapshot' are individually well-documented in the schema, so the description does not need to elaborate, but it also does not provide higher-level context (e.g., typical combinations).

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 clearly states the tool's purpose: generating a single-step evidence package (v2.0) that aggregates screenshots, DOM summaries, errors, network requests, API response summaries, data diffs, traceId, console logs, page errors, HAR, and existing artifacts into a JSON file for dual-chain verification review. It uses a specific verb ('生成') and resource ('单步证据包'), and distinguishes itself from sibling tools by focusing on evidence aggregation for review.

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 provides no explicit guidance on when to use this tool versus alternatives, nor does it mention prerequisites or when not to use it. Among the many sibling tools (e.g., browser_step, evidence, evidence_index), there is no discussion of trade-offs or context for selection. The usage is only implied through the detailed list of what it aggregates.

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