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

Annotations already declare readOnly/idempotent/non-destructive, and the description layers on real operational detail: robots and partner test clicks are excluded and surfaced in `excluded`, results become a lower bound with `truncated: true` past 50 000 rows, and a Supabase access token plus a shop from list_my_shops is required. That is exactly the beyond-annotation context an agent needs before calling.

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 but front-loaded block: the core question comes first, then scope, exclusions, truncation, and auth constraints. Every clause carries information, though the single run-on structure makes it heavier to parse than a short sentence list would 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?

With no output schema, the description carries the full burden and does so: it describes the returned total, the zero-filled daily series, the country and channel dimensions, the `excluded` and `truncated` fields, and the precondition of authentication plus shop ownership. Nothing material for a correct call 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; the description earns more by adding semantics the schema lacks: both bounds are inclusive, dates are UTC days, the default is the last 30 days, and the window is capped at 366 days. It also ties `shop` to its source of truth (list_my_shops).

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 precise verb+resource framing ('How many people Fordeal sent to the shop') and immediately enumerates the exact breakdowns returned: total, per day, per delivery country, per channel. It also draws a hard boundary against adjacent concerns ('no orders or revenue are estimated (own-programme orders are in the partner portal)'), so an agent can separate it from feed/registration siblings without inspecting 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?

Usage context is strong: default window is the last 30 days, max 366, UTC days inclusive, and alternative shops answer 403. It also signals when-not by redirecting order/revenue questions to the partner portal. It stops short of naming a sibling tool for a related traffic question, so it is clear context rather than full alternative routing.

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