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

Beyond the readOnly/idempotent annotations it discloses the statistical method, the confidence level attached to each finding, the evidence fields (value, baseline, ratio, sample_size), the workspace-timezone convention for days/times, and the minimum-sample guardrail that prevents fabricated results. These are real behavioral traits an agent cannot infer from annotations or schema.

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?

One dense paragraph, front-loaded with what the tool produces before the caveats and the usage hint. The parenthetical reason codes (low_reach, low_engagement_rate) are informative, though the enumeration of formats and fields makes it heavier than it needs to be.

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?

There is no output schema, so the description must carry the return shape, and it does: finding categories, per-finding evidence, confidence, and the enough_data: false signal. Combined with the timezone and minimum-sample notes, an agent has everything needed to call it and interpret results 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 coverage is 100%, with bounds and the default 90 already documented for 'days' and the list_workspaces origin for 'workspace_uid'. The description adds only the timezone context, not parameter-level meaning, 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 a specific verb and resource ('findings from the workspace's own published posts') and pins down the method ('computed with simple statistics (no AI)'), which separates it from the raw-analytics siblings like get_post_analytics or list_post_analytics. It also enumerates the exact finding types produced, so an agent knows what it gets without opening a schema.

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?

Gives a concrete downstream use ('suggest what, where and when to post, or edits to scheduled posts (list_posts)') and a hard precondition (fewer than 10 published posts returns enough_data: false). It never explicitly contrasts itself with get_post_analytics/list_post_analytics, so the choice between raw metrics and computed findings is left implied.

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