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

With no annotations, the description carries the full burden and does: bounded 16-source live window, two sources per page, non-exhaustive/non-snapshot semantics, 503 when deployment is disabled, no member actions or click attribution, and observed_at/expires_at staleness rules on every price.

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?

Front-loaded with the purpose and dependency, and the dense operational clauses (window, offsets, staleness, 503) each earn their place. It is long, but the length is justified by the number of distinct behaviors an agent must know.

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 complex, non-snapshot, gated read tool with no output schema, the description covers return shape (golf-offer.v1, check_price, unknown currency), pagination, staleness, and failure modes. Nothing material an agent needs before calling 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 description coverage is 100%, so all three parameters are already documented in the schema, including variant_id null behavior and the offset bounds. The description restates the next_offset/window semantics and adds little syntax beyond what the schema provides, so the baseline 3 applies.

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 verb chain (discover sources, then verify through the commerce gate) tied to a canonical product ID sourced from search_products. An agent can tell this is the batch verification path and that it is gated rather than a raw catalog read.

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?

Explicitly tells the agent to supply the exact variant UUID to get offers and that omitting variant_id yields selection metadata instead, plus directs use of next_offset. It does not, however, route against the singular sibling get_verified_offer, leaving the batch-vs-single choice implicit.

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