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

Annotations already establish readOnly/not-destructive/openWorld, so the description's value is in the extra semantics it supplies: the partial flag meaning a network failed to respond, the instruction not to render missing data as zero, and the fact that each call already bundles every network for every post. These are real behavioral traits an agent would otherwise get wrong. It does not discuss rate limits or what scheduled posts section looks like, but the output schema covers returns.

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 front-loaded with what the tool returns, then moves to the period, then to the partial-flag caveat and the batching rule. Every sentence contributes something actionable and none repeat the schema. It is dense but not padded.

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 stats tool with an output schema and full schema coverage, all the pieces an agent needs are present: scope of metrics, per-network breakdown, partial-result handling, and the single-call-per-period rule. Safety is carried by annotations and return shape by the output schema, so nothing material is missing from the description.

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 from/to, limit and brand_id are already documented, and the description only restates that the period is optional. It adds no format or interaction detail beyond the schema. Baseline 3 is appropriate 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?

The description names a concrete deliverable: metrics (vistas, me gusta, comentarios, compartidos, alcance) for a brand's most recent posts, broken down per network, plus totals and upcoming scheduled content. That is specific and unambiguous. It stops short of comparing itself with sibling tools such as compare_posts or get_account_stats, so an agent must infer the boundary itself.

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?

Strong operational guidance: ask for the full period once, do not make one call per post, and do not retry. It also tells the agent to treat partial=true as incomplete data rather than zero. The only gap is that no alternative tool (for example compare_posts for cross-post comparison) is named as the thing to use instead when this tool is not the right fit.

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