poll_watchlist

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

With annotations only telling us it is a non-destructive, non-readonly, closed-world call, the description adds the real behavioral contract: first-run baseline creation, repeated return of pending batches until acked, no checkpoint advance on backlog or upstream failure, and no persistent background execution. This is exactly the stateful nuance an agent needs.

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?

Five tight clauses, purpose front-loaded, then behavior and the ack requirement, then the no-background constraint. Every clause carries information and none is padded.

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?

Behavior is well covered for a stateful polling tool absent an output schema, and the batch-repetition note hints at return shape. However, with 0% parameter coverage and no output schema, an agent still lacks the meaning of id, delivery_limit, include_initial, and per_session_limit.

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% across four parameters (id, delivery_limit, include_initial, per_session_limit). The description never explains any of them beyond a vague nod to first-run baseline behavior, leaving the agent to guess at id format and the two limit semantics from the schema alone.

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 (检查/poll) and resource (指定关注列表各群的新消息), which cleanly separates it from generic siblings like check_new_messages or read_wechat_post. It also adds scope qualifiers (first-run baseline, one round per call). It does not name any sibling explicitly, so it stops short of a 5.

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?

Gives concrete operational guidance: call once per round rather than backgrounding it, and ack batches only after reading fully. The ack/re-read workflow implicitly routes the agent to the read/ack sibling tools, but no alternative tool is named and no explicit when-not condition is given.

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