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

Annotations only declare readOnlyHint and openWorldHint, so the description adds real behavioral context: fixed pagination of 20 providers per page, the concrete payload fields returned, and the cross-tool dependency for filter values plus the comma-separated list syntax. It does not mention rate limits, total result caps, or auth requirements, but the added value over annotations is substantive.

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?

Two sentences, front-loaded with purpose and result shape, then the filter-sourcing rule. Dense but every clause carries information; the only minor cost is that the second sentence packs five filter names plus delimiter syntax into one line.

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 enumerated (the description does so anyway), and annotations cover the safety profile. The gap is the 16-parameter surface at 0% schema coverage: nearly half the params (age, gender, rating, sort, distance, page, availability, affirming_care) are undocumented in both schema and description, which an agent needs in order to invoke this search correctly.

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 0% across 16 parameters, so the description carries the burden. It explains the sourcing and format of the filter-style parameters (insurance, insurance_plan, language, clinical_focus, affiliated_hospital) and list delimiters, but says nothing about age, gender, rating, sort, distance, page, availability, or affirming_care. Partial compensation only.

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 (Search) plus the resource (Healthgrades physicians) and the qualifying axes (specialty, condition, procedure, name, near city/ZIP). It also discloses the result shape (20 providers per page with NPI, specialty, office, rating, insurers, profile URL, filters), which cleanly separates it from healthgrades_physician (single-provider detail) and healthgrades_physicians_filters (filter enumeration).

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 routes the agent to healthgrades_physicians_filters for the valid values of insurance, plan, language, clinical_focus, and hospital filters using the same query/where, and states that list filters take comma-separated values. It does not, however, spell out when to prefer this search over healthgrades_facilities_search or healthgrades_physician.

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