channel_mentions

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

No annotations are provided, so the description carries the burden. 'Get' implies a read-only query and the note on the two name forms is a useful matching behavior, but it discloses nothing about scan scope (which channels/time range) or result ordering that an agent calling this would benefit from. Adequate but with clear gaps.

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?

Two sentences, purpose front-loaded and the matching note following it. No wasted text; nothing needs trimming.

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 both simple parameters are fully documented. The description is nearly complete; the only omission is the scope of the scan (all channels vs. a specific one), which would matter for a mention-search tool.

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 100% and the schema already documents both limit and agent_name, including the note that the '@' prefix is optional. The description's sentence about the two notations simply repeats what the schema states, so it adds no meaning beyond the structured field. Baseline 3.

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 (Get), resource (channel messages), and scope (those mentioning a specific agent). This clearly distinguishes it from read-oriented siblings like channel_read and channel_unread, though it does not name those siblings explicitly.

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: an agent needing messages that reference it would reach for this. However, there is no explicit when-to-use/when-not guidance and no mention of alternatives such as channel_read or channel_wait, leaving selection to inference.

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