Read who is mentioning you on X

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

Annotations already cover readOnlyHint, openWorldHint, and destructiveHint, so the description doesn't need to restate those. It adds meaningful behavior: costs credits per mention returned, orders newest first, and requires an X connection. These traits are not derivable from annotations and inform the agent about side effects (billing) and execution context. It could mention pagination or error behavior, but those are less critical for a read operation.

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 description is four sentences, each contributing distinct information: purpose, use cases, cost/billing warning, and prerequisite. It is front-loaded with the core function and avoids redundancy. While slightly dense, it remains efficient and every sentence earns its place. Slightly more structure could split use cases from cost advice, but overall it is concise.

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 read-only tool with full schema coverage and annotations, the description provides all needed context: exact purpose, use cases, ordering, cost implications, prerequisite, and a pointer to the follow-up reply tool. Since there is no output schema, the description doesn't need to explain return format. An agent can correctly invoke this tool and make informed decisions about pagination and cost, making it complete.

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 input schema covers all 3 parameters with full descriptions (sinceId, maxResults, paginationToken), so the baseline is 3. The description adds cost semantics directly tied to maxResults, warning that every mention is billed and advising to keep it small. It also reaffirms the default of 10, which the schema states. This extra context about billing and page size adds value beyond 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?

The description states a clear verb 'Read' and resource 'posts mentioning the connected X account', and goes further to specify the content ('who is talking to the brand, in their own words, newest first'). It distinguishes the tool from siblings by describing a unique function (reading mentions) not covered by other X tools like list_x_dms or x_post_metrics. The purpose is unambiguous and specific.

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?

Provides explicit use cases: 'find what deserves a reply' and 'mine real objections and customer language for ad copy'. It also gives a follow-up action (reply with post_to_x + replyToId), cost-control advice (keeping maxResults small), and a prerequisite ('Needs X connected'). This gives clear when-to-use guidance and even suggests alternatives for the next step, making it easy for an agent to decide when to invoke this tool.

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