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

Beyond the readOnly/non-destructive/closed-world annotations, the description discloses substantive behavior: windowed figures are computed identically to the dashboard, lifetime visitors are an HLL estimate with ~1.6% error, lifetime revenue comes from the payments ledger, and gated columns return null with a note rather than failing. The null-instead-of-error behavior is exactly the kind of detail an agent needs to interpret partial results.

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?

It is a single dense paragraph, front-loaded with the deliverable and then the data-provenance caveats, with no filler sentences. Some content duplicates the schema (the window list, the rolling-window definition), which costs a little efficiency but keeps the description self-contained.

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 so: it enumerates the columns, states that products and scores are always present, and explains that gated columns come back null with a note. For a four-optional-parameter read tool, nothing an agent needs in order to call it or interpret the response is missing.

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 the baseline is 3, but the description adds meaning: it lists the metric set that sortBy/order operate over and clarifies that products missing the chosen metric sort last. The window semantics are already spelled out in the schema, so the description's added value is incremental rather than essential.

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 names the resource (all your products, side by side) and enumerates the exact metrics returned — unique visitors, views, revenue with refunds netted, ARPC, RPV, scan scores — so an agent knows precisely what this produces. It stops short of explicitly differentiating itself from list_products, search_products, or get_product, leaving the comparison-vs-listing distinction 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 metrics roster and sorting capability suggest it is for multi-product metric comparison rather than single-product lookup or search. There is no explicit statement of when to prefer this over list_products or search_products, and no stated exclusions or prerequisites beyond the subscription gating note.

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