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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description adds genuinely useful behavior: default returns all websites capped at 30, a cell returns {error} when a source is not connected, and output has a merchant-wide totals block. What's missing is whether 'export' produces a file or returns inline data.

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?

Content is front-loaded with the key scope sentence, and every clause adds factual value about row contents or behavior. It reads as a dense run-on with semicolons rather than a crisply structured definition, but 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?

No output schema exists, so the description appropriately explains the return shape (one row per website, totals block, error cells). The main gap is the export mechanism itself — whether the caller receives JSON data or a downloadable artifact — which is essential for correct invocation.

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?

With 0% schema description coverage, the description must carry the load, and it does: days is constrained to 7/28/90, and both seliee_website_ids and seliee_website_uuids are described as narrowing filters. It doesn't clarify the relationship between ids and uuids (precedence, union, or why both exist), which is the one remaining ambiguity.

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 opens with a specific verb and resource ('[read] KPI dataset') and then enumerates exactly what a row contains: Search Console totals vs previous period, ad spend/results, PageSpeed, AI visibility, plus merchant-wide totals. An agent can tell this apart from narrower siblings like get_website_report, get_leads_report, or get_pagespeed_summary.

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?

Implicit usage is clear (pull a combined cross-source KPI snapshot), but the description never states when to prefer it over the many single-source report siblings, nor any exclusions or prerequisites. The agent must infer that this is the aggregate alternative rather than call the individual report tools.

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