zulip_mentions

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful behavior beyond that: a hard cap of 10 results and 300-character truncation per message, which tells the agent to expect short, lossy content and no pagination.

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 front-loaded sentence with no filler; the result cap and truncation length are the two facts that matter and both appear immediately.

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?

For a zero-parameter read tool with annotations and no output schema, the description covers what is returned in broad terms (count, truncation, mention filter). It stops short of saying which stream or how results are ordered, which leaves a small gap.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate at the schema level; baseline 4 applies. The fixed limits are stated in the description rather than exposed as inputs, which is consistent.

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 resource and scope: the 10 most recent messages that mention this bot, truncated to 300 chars. That distinguishes it from zulip_read and zulip_search by content type (mentions of the bot). The phrase 'in the stream' is slightly ambiguous without a stream parameter, keeping it 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?

No guidance on when to prefer this over zulip_read or zulip_search, and no note that it cannot be filtered or paginated. The agent must infer that this is the lightweight 'did anyone ping me' call rather than a general message retriever.

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