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

Annotations only declare readOnlyHint and openWorldHint=false; the description goes well beyond by disclosing data freshness ("refreshed about hourly"), null semantics (network doesn't report, no earlier data), and the needs_reconnect error state. Those are exactly the behavioral facts an agent needs before trusting or retrying the output.

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?

Front-loaded with the resource and period scope, then moves to purpose, then to freshness/null/error caveats in short sentences. The opening sentence is dense with enumerated metrics but every item listed is a genuine return field, so little is wasted.

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 return-value burden and does it: it lists the result sections, explains null meanings, notes the previous-period comparison, and flags the reconnect condition. Nothing material is missing for a zero-required-parameter read tool.

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 coverage is 100%, so all three parameters (days enum, limit, account_ids) are already documented in the schema. The description restates the 7/30/90 periods and top-posts concept but adds no syntax or edge-case meaning beyond what the schema 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?

States the resource (connected accounts' and Sendhour-published posts' performance) and enumerates exactly what is returned: totals, per-account views, engagement breakdown, followers, posts published, prior-period comparison, and top posts. The verb is soft ("how ... did"), but no sibling tool covers analytics, so the resource alone makes it unambiguous.

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?

"Use it to learn what performed best before planning new posts" gives a clear usage context tied to a workflow. It stops short of naming explicit exclusions or alternatives (e.g., it doesn't say to use list_posts for raw post data), which keeps it from a 5.

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