channel_mentions

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses the matching behavior and a historical bug/fix ('2026-09-08 前这里只匹配 "@"+名'), which is unusual but real behavioral context. However, it says nothing about ordering, pagination, permissions, or what happens at the limit boundary, and the changelog detail is only marginally actionable for an agent selecting the tool.

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 first sentence is a clean, front-loaded purpose statement, but the remainder is a historical changelog embedded in two languages, including a parenthetical about a bug fixed before a specific date. For an agent invoking the tool, the historical rationale does not earn its place and dilutes the signal.

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 an output schema present, return values need not be explained, and the parameter surface is small. But the description omits ordering, default sort, and how mentions are detected (substring vs token), so an agent cannot fully predict behavior. Adequate but incomplete.

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 both agent_name and limit are already documented in the schema. The description adds the '@'-optional matching rule, which is already echoed in the schema, so it adds little beyond the structured field. Baseline 3 applies when the schema does the heavy lifting.

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 and resource: 'Get channel messages that mention a specific agent.' This clearly distinguishes it from channel_read (all messages) and channel_send. It doesn't explicitly name sibling tools, which is why it sits at 4 rather than 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?

The description explains the matching semantics (bare name vs '@name') but gives no when-to-use guidance, no mention of how it differs from channel_read or channel_unread, and no exclusions. An agent must infer that this is the mention-filtered variant of channel_read.

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