cvs_search

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

With no annotations provided, the description carries the full behavioral disclosure burden and does it well: it details the one-page containment of products, fields returned (current/original price, sponsored/featured/new-product flags, facet data), the geo constraint, and the upstream error rather than empty result behavior. It doesn't disclose rate limits or auth needs, but as a read-only search these are minor omissions.

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 and information-dense: purpose, return shape, facet structure, sibling relationship, scope, parameter role, and geo constraint appear within five sentences. Minor redundancy of the non-prescription scope remark ('non-prescription retail/OTC catalog' and 'covers the non-prescription retail catalog only') prevents 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?

Complete for a moderate-complexity read tool with no output schema: the description explains what gets returned (attributes of fields, facets, one page granularity), pagination, scope limits, and failure mode. It could add page range end behavior and rate limits, but these are acceptable trade-offs given length.

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?

Input schema coverage is 100%, so the schema already documents all three answers; the description mostly restates q and page with moderate added value. The one genuine addition is the cross-reference that sort values match cvs-category's Sort By values, which supports consistent multi-tool use.

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+resource+mechanism ('Search CVS OTC products by keyword') and names the sibling differentiation: it is the same product-search backend cvs_category reads, reached by keyword rather than category/brand path. The stated return contract (normalized products with title, brand, price, flags, total count, facets) makes the tool's job unmistakable.

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 when to use this vs the cvs_category tool: keyword search instead of a category/brand path, and notes it covers only the non-prescription catalog, establishing a when-not boundary. It also warns that US/US-territory egress is required, so an agent can avoid a regional mismatch before calling.

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