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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), but the description adds material behavior beyond them: data provenance (Bluesky, Mastodon, Facebook, Instagram), a 30-day post-publication read window, and that X, LinkedIn and TikTok report available: false. The 'never compare them on these numbers' caution is a genuinely useful constraint not derivable from any structured field.

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?

Purpose and payload are front-loaded before the usage guidance and the caveats, and nothing is padding. The single long semicolon-chained sentence is dense and slightly harder to scan than it needs to be, but the content justifies the length.

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 no output schema, the description carries the full burden of describing the return shape, and it does so thoroughly (totals, per-network metrics with follower change, per-day interactions, best posts). Combined with the coverage caveats for unread networks, an agent has everything needed to call it and to interpret the result honestly.

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%, and all three parameters (from, to, top) are documented in-schema including their defaults. The description restates the 'default: last 30 days' period but adds no syntax or meaning beyond what the schema already provides, so the baseline 3 applies.

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?

Opens with a specific verb and resource ('Returns how published posts did over a period') and then enumerates the concrete payload: totals, per-network metrics, interactions per publication day, and best posts. It is immediately distinguishable from get_post, which it explicitly names as the single-post alternative.

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?

States the triggering user intents ('what worked', 'which network or which post performed best', picking next topics and times) and gives an explicit exclusion routing the agent to get_post for one post's numbers. Both the when-to-use and the alternative are spelled out.

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