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

With no annotations, the description carries the full burden, and it delivers extensive behavioral disclosure: the BUY-74597 degraded contract explains exact meta fields (status, emptiness_reason, degraded_kind, confidence, diagnostic.timed_out_stage), states that it never returns an unqualified empty result on timeout/auth/upstream failures, and instructs agents to branch on meta.degraded. This is unusually transparent about edge-case behavior.

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 description is longer than average, but it is front-loaded with the core purpose and arranges the additional content logically: required-like delivery context, return fields, market scope, compact recommendation, then the degraded contract. The degraded-contract paragraph is dense but essential for correct agent behavior, so the length is justified.

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?

Given 15 parameters, no annotations, and no output schema, the description is quite complete: it covers return fields, market coverage, the deliver_to requirement, and the non-trivial degraded-response contract while leaving parameter details to the schema. It is missing sibling differentiation versus search_products_v2 and any explicit pagination/rate-limit notes, but overall it is sufficient 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?

Schema coverage is 100%, so the baseline is 3, but the description adds real semantic value: deliver_to's precedence and its role in preventing all-market scans, plus compact=true as the agent-optimized shape with normalized_price_usd. It does not re-explain every parameter, but the schema already covers their syntax and defaults.

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?

States a specific action on a specific resource: "Search the BuyWhere product catalog by keyword." It also describes the return payload (product records with title, description, image, price, merchant) and the geographic scope, so an agent can clearly distinguish this from siblings like compare_products or find_similar.

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?

Provides strong usage context: deliver_to is "REQUIRED for buyer-facing use," takes precedence over country_code/country, and prevents all-market scans; compact=true is recommended for agent use. However, it never names alternatives like search_products_v2 or states when not to use this tool, so it stops short of explicit exclusion/alternative guidance.

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