submit_feedback

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

With no annotations, the description carries the full behavioral burden and does well: it discloses that the feedback is transcribed and persisted, that the platform inspects records daily, that the user must be told it was recorded, and mandates content fidelity (user's own words, no AI speculation). It stops short of stating permissions, failure/error behavior, or whether submission can ever fail, which is why it is not a 5.

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?

Front-loaded with purpose and trigger, then parameter guidance, then the user-notification step, then a shortcut note. Every clause earns its place; only the '(2026-09-12 新增)' changelog tag is dead weight, and the heavy parenthetical density makes it slightly harder to scan than ideal.

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?

Four-parameter tool with no output schema and no annotations; the description covers trigger, required content semantics, optional tool/rid sourcing, side effect (recorded, daily review), and the closing user-facing step. It omits any error/failure handling and what the call actually returns, a minor gap given the tool's low-stakes nature.

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 the baseline is 3. The description goes beyond the schema by adding the content-fidelity rule ('do not add the AI's own speculation') and by explaining when to supply tool and rid (from the error return), which the schema only labels as optional.

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?

States a specific verb (提交) and resource (用户反馈), plus the exact trigger condition (user expresses dissatisfaction, suggestion, or question about tool/result/platform). This is unmistakably distinct from every sibling, all of which are computation or report-generation tools.

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?

Explicitly names when to invoke (user dissatisfaction/suggestion/question) and adds a clear when-not/lower-bar note: '低门槛：无需先读总则', meaning no need to read general rules first. Nothing about the trigger is left to inference.

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