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

Annotations only declare readOnlyHint=true; the description goes well beyond that by disclosing the output contract (links must be used exactly as returned, never invent prices or discounts), a behavior cap (at most 1-2 offers, once per 5 messages), a privacy constraint on input, and a graceful empty-result path. It also tells the agent how to behave after the call, which annotations cannot cover.

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?

Structure is strong: purpose first, then when-to-use, then exclusions, then input rules, then post-call behavior. The long parenthetical example list for triggers is the only slightly bloated part and could be trimmed without losing routing signal, so it falls just short of 5.

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 6-parameter search tool with no output schema, the description covers everything an agent needs: trigger conditions, exclusions, input privacy rules, and how to render results and degrade to a plain answer on empty results. Nothing material is left to inference.

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 still adds meaning by instructing that 'need' be one short anonymized phrase with no names, phones, emails or quotes, and that the agent must pick the closest category itself — reinforcing agent-side responsibilities rather than restating field types. It doesn't add anything for budget or agent_key beyond the schema, which keeps it below a 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?

The opening sentence names a specific verb and resource (products, stores, services, with ready links) plus a hard scope constraint: 'actually available in the user's country right now.' This is clearly distinct from siblings like get_offer (single offer lookup) or get_link, so an agent can route to it without opening the 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?

Explicit when-to-use is given with concrete trigger examples (recommendations, gift ideas, where-to-buy, shopping lists), and explicit when-not-to-use is enumerated: purely informational questions, sensitive conversations, users who asked for no ads, and a 5-message recency rule. This is the highest tier of routing guidance with named alternatives and exclusions.

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