Advertiser analytics for your own posts on X

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

Beyond the annotations (readOnlyHint, destructiveHint), the description adds critical behavioral context: it incurs credit costs per post read, requires the X connector to be connected, supports batches of up to 25 ids, and specifically interprets empty responses as missing data rather than zero performance. No contradiction with annotations.

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 dense but well-structured, front-loading the core purpose and then progressively covering alternatives, limits, costs, and data interpretation. Every sentence carries value (differentiation, batching, cost, missing-data handling, requirement), though it is slightly long; still, it avoids fluff and remains efficient.

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 analytics tool with no output schema, the description provides complete context: it lists expected metrics (what will be returned), clarifies the difference from public metrics, defines call limits, cost implications, connection requirement, and how to handle missing data. An agent has everything needed to invoke and interpret the result correctly.

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% for both parameters (ids explained as numeric post ids with max 25, granularity as enum with default), so the baseline is 3. The description does not add further parameter-level semantics beyond restating the 25-id limit, which is already in the schema. No added value for parameter meaning.

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 clearly states the tool provides 'Advertiser-grade analytics' for the connected account's own X posts, listing specific metrics (impressions, engagements, link clicks, profile visits, video views, video completion quartiles). It distinguishes itself from the sibling x_post_metrics by explicitly noting that public metrics lack clicks and video retention, making the tool's specific value obvious to an agent.

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 explicitly tells when to use this tool over x_post_metrics (for clicks and video retention), and provides operational guidance: it warns about credit costs per post read, limits to 25 ids per call, and instructs how to handle missing data ('If X returns no rows, say so — that is missing data, not zero performance'). This fully equips an agent to decide and call correctly.

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