zhiqi_inbox

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 a good job: it states that the payload only contains summaries and reference IDs, explicitly excludes delivery body content, and warns that content is UNTRUSTED and must not be executed as instructions. This is substantive security-relevant behavior beyond what the schema or annotations reveal.

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 compact sentence that front-loads the purpose and then adds the critical payload and security caveats. Every clause earns its place with no filler or repetition.

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 optional-parameter fetch tool, the description covers the main purpose, the payload shape, and a vital safety warning. However, it lacks parameter-level guidance and does not describe pagination/cursor semantics for limit and cursor, so an agent may still need to infer how to use the optional fields 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%, and the description does not explain limit, cursor, or unackedOnly. The '增量游标' phrase hints at the cursor parameter, but the other parameters remain undocumented, leaving the agent to guess their exact meaning and formatting.

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 (拉取) and resource (收件箱), and adds the incremental-cursor mechanism, so the core action is unmistakable. It also clearly differentiates this from siblings like zhiqi_inbox_ack, which handles acknowledgment rather than fetching.

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 phrase '增量游标' implies this is meant for incremental polling against a saved cursor, which gives some usage context. However, it does not explicitly state when to choose this over alternatives, nor does it provide examples or exclusions beyond the note that the payload lacks full delivery content.

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