find_patients

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

Annotations already declare readOnly, idempotent, non-destructive, open-world behavior, so safety is covered. The description adds genuinely useful non-obvious behavior: one page per call and the instruction to follow next_offset even when a filtered page is empty. It does not disclose match semantics (exact vs partial) or how multiple criteria combine, which is the remaining behavioral gap.

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-loads the core verb and the hard precondition, then states the DOB format and pagination rule in short sentences. Every sentence carries information, though the pagination note could be tightened slightly.

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?

Output schema exists, so return-value explanation is not owed. Pagination and criterion requirements are covered, but for a 7-parameter, zero-coverage search tool the missing matching semantics (partial vs exact, AND/OR across criteria) leave an agent guessing about result behavior.

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 description coverage across 7 parameters, the description must carry the load. It supplies the birthdate format (YYYY-MM-DD) and establishes that at least one criterion must be nonblank, but says nothing about how email/fname/lname/phone are matched or combined, and limit/offset semantics come only from schema defaults.

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 and resource ('Search patients'), which separates it from the get_patient/get_appointment single-record siblings. It does not explicitly name an alternative for ID-based lookup, so sibling routing is implied rather than taught.

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?

Gives a hard precondition for invocation ('at least one nonblank criterion is required'), which is clear when-to-use guidance. It stops short of naming when-not-to-use or which sibling to prefer, so it is clear context without explicit alternatives.

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