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

Annotations already establish readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real behavioral context beyond that: comparisons against the prior window, a per-account vs all-accounts split, top-3 post inclusion, and a 'thin' data flag that changes how results should be reported.

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?

Dense but every clause carries information about output content or reporting rules; little is wasted. The structure is a bit run-on and the output-handling instructions (quote numbers, caveat thin data) are appended rather than separated, but it remains readable.

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 burden of explaining returns and does so thoroughly: per-account metrics, prior-window deltas, top posts, and account-wide aggregates. Only the thin/no-explicit-sibling boundary and any pagination or latency behavior are unaddressed.

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 both `days` (default 7, max 90) and `profile_ids` (omit for all) are already fully documented in the schema. The description restates the default and scope but adds no format or semantic detail beyond the schema, so 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?

The description enumerates exactly what the tool returns per account (comments, replies, DMs, contacts, emails, prior-window comparisons, top 3 posts) plus account-wide view/engagement changes, which is far more specific than the name. It does not explicitly distinguish itself from siblings like sprkly_get_analytics or sprkly_get_account_summary, leaving that differentiation to inference.

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?

Usage is only implied: the presence of a `days` window and per-account breakdown suggests it is the engagement report, but there is no explicit when-to-use versus get_analytics/get_account_summary. The instructions about quoting current/prior numbers and caveating thin data are output-presentation guidance, not invocation guidance.

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