读取已暂存的移动端证据

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds content context (compressed/annotated screenshots and selected logs) but does not disclose return format, error behavior, or what happens for an invalid evidenceId. No contradiction with annotations.

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?

One front-loaded sentence with no filler. It states the operation, resource, and contents efficiently, so every word earns its place.

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 simple one-parameter, read-only operation with strong annotations, the description covers what the tool reads and what is inside. It is adequate for invocation, though it leaves when-to-use details to the agent's inference.

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%, so the description needed to compensate for the undocumented evidenceId parameter. It never mentions evidenceId, how to obtain it, or how it selects the package; the mapping is only inferable from the field name. This is a meaningful gap for a required parameter.

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 uses a specific verb ('读取' / read) and a specific resource ('Dashboard 暂存的证据包' / evidence package staged in Dashboard), and it enumerates the package contents. This clearly distinguishes it from sibling tools like mobile_capture or mobile_get_logs.

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 gives no explicit guidance on when to use this tool versus alternatives, no prerequisites, and no mention of a preceding step like mobile_capture. Usage is only implied by the phrase 'staged evidence', so an agent has to infer the right timing.

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