mkt_inbox

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

No annotations are supplied, so the description carries the full behavioral burden. It does state '只读' (read-only), which is the single most important safety fact, and it identifies the data source behind each channel. However, it says nothing about authentication needs, rate limits, or what the inspection returns (messages, findings, flags), which is a real gap for a scan tool with zero annotation coverage.

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 with the read-only constraint and channel set front-loaded, followed by the per-channel clauses. Nothing is redundant. The telegraphic style is compact but borders on cryptic for non-Chinese readers, which keeps it slightly below top marks.

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?

With no annotations and no output schema, the description is the only source of behavioral information. It covers the read-only guarantee, channel semantics, and the conditional repo need, but leaves the return shape and output of the '巡检' undefined, so an agent knows how to call it but not what to expect back.

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 coverage is 50%, with repo documented in the schema but channel's enum values left unexplained. The description compensates well by giving each enum value a source meaning (hn, github, email/Gmail, x/vendor inbox) and by adding a conditional requirement ('github 需 repo') that the schema does not express, since only channel is marked required.

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 pairs a specific verb ('只读...巡检' – read-only inbox/first-response inspection) with a named resource and enumerates the four channels it covers. An agent can tell it is an inbox-scanning tool rather than a search or planning tool. It stops short of naming a sibling it must not be confused with, since none of the listed siblings is an inbox tool.

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?

Usage is implied through per-channel conditions: github requires a repo, hn reads new replies on submitted items, email scans Gmail, x scans the vendor inbox. That tells the agent which channel to pick for which source, but there is no explicit when-not guidance or comparison against I/O-oriented siblings such as mkt_retro_scan or mkt_followup_due.

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