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

Annotations already mark it read-only/idempotent/non-destructive, and the description still adds substantial behavior: marketCategories is ordered by score DESC with the first being dominant, score is 0–1 confidence and source is ai|manual, the list is empty when uncategorised, and null stats mean not-yet-computed with metricsSyncedAt indicating freshness. That is real disclosure beyond the annotation block, not a restatement of it.

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?

Purpose is front-loaded in the first sentence, then return shape, then field semantics, then the recommended workflow — a logical order with no filler. It is dense and long, but nearly every clause carries information an agent needs given there is no output schema; only the inline type-listing of the return object could be tightened.

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 explain the return payload — and it enumerates every field, its units (prices in `currency`), its range (score 0–1, eanFillRate 0–1), its enum forms (ai|manual, none|low|medium|high), and its null semantics. Combined with the sibling routing and the optional-parameter fallback, an agent has everything needed to call it and act on the result.

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 0% and the single parameter has no schema description, so the description must carry the load — and it does: project_id is optional, inferred for single-project customers, and when project_id_required is set the agent should call list_projects first. That is exactly the inference behavior an agent cannot derive from `type: integer, exclusiveMinimum: 0`.

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?

Opens with a specific verb and resource ("Get a project's catalog product profile") plus the downstream intent ("so you can suggest suitable sales channels"). It is clearly distinguishable from the many list_*/get_* siblings because it names the exact object returned (vertical classification + catalog stats) rather than a generic project or channel record.

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 an explicit trigger ("Use this when the user asks which sales channels fit their catalog") and then a full routing path: cross-reference list_marketplace_channels / list_ad_channels, propose only channels whose `available` is true, then walk the create/configure wizard. It also states a negative constraint ("Never invent channels that aren't in the catalog") — a genuine when-not rule.

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