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

Annotations only declare readOnly/openWorld, but the description adds real behavioral context: the dual-mode response shape and a specific warning that search_history is NOT session-scoped and should be treated as fixed default content. That caveat prevents a likely misinterpretation and is exactly the value structured fields can't provide.

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?

Three sentences, front-loaded with the core purpose and the mode-selection rule; each sentence adds non-redundant information. Slightly wordy phrasing ('confirmed NOT session-scoped', 'the real response') keeps it from a perfect score.

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?

An output schema exists, so return values need not be explained, and the description still covers both invocation modes and the one return-value gotcha (search_history). Nothing an agent needs to call it correctly 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?

With 0% schema coverage for the single query param, the description carries the burden, and it does: it explains the semantic effect of providing, omitting, or emptying the query (two different result sets). It doesn't specify format constraints or length limits, so not a full 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?

States a specific resource ('search-box typeahead suggestions') with a specific verb behavior, and immediately distinguishes itself from a full search tool by describing suggestion/merchandised output. An agent can tell this apart from hm_search without opening either 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?

It clearly routes the caller between the two modes ('with a query given' vs 'query omitted or empty'), which is the key usage decision. However, it never explicitly names hm_search as the alternative for full product search, 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.