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), and the description adds materially beyond them: auth behavior with the order reference versus anonymous use, rate limits (meaning-based search limited in the first searches per 10 minutes, then words only; at most 30 searches per 10 minutes), and the 10-row cap on details. It also discloses output semantics: live stock in packages, a pricing block in EUR plus pricing.local in storefront currency, and that photo descriptions are observations, not guarantees.

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?

The highest-value content — what the tool searches and the one-call completeness claim — is front-loaded, and almost every clause carries operational information. However, the middle section is a single dense paragraph of parenthetical fragments that is harder to parse than it needs to be for a 17-parameter tool.

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?

For a 17-parameter tool with nested objects and no output schema, the description does the necessary work: it describes the row shape (stock, pricing blocks and currencies, facet labels, stored facts with 'use' permissions, photo observations), the details escalation with its row cap, quantity adding for_quantity, and the auth/rate-limit envelope. An agent has enough to call it and interpret the response correctly.

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 88%, so the baseline is 3, but the description adds real meaning: natural_query searches by meaning in any language and in storefront language, keywords hit the Dutch catalogue text and broaden when multiple, ids and codes are exact and ranked first with codes matching any written form, and similar_to distinguishes blend (shared theme) from each (alternatives per seed, seed excluded). Sort, offset, limit and facets receive no added explanation, which keeps this below 5.

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 ('Search the wholesale range') and enumerates the product domain (toys, gifts, party supplies, seasonal, grabbelton, viral items), so an agent can immediately tell this is catalogue search rather than order lookup or product lookup. It also implicitly distinguishes itself from siblings like product_details and categories by covering discovery.

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 when-to-use rule ('Use it for any business purchasing question about these products, also when the shopper doesn't name the store') and an escalation path ('For a question the context does not answer, call again with ids and fields ["details"]'). What it lacks is direct routing against named siblings such as product_details or categories for single-item lookups, leaving that inference to the agent.

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