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

Annotations already declare readOnlyHint=true and openWorldHint=false, covering the safety profile. The description adds useful behavioral detail beyond the annotations, stating that results include full listings with address, phone, and doctor 'as on file' and that match count is returned for paging. It does not discuss rate limits or auth, but for a read-only search tool the added return behavior is meaningful.

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?

The description is two sentences with no filler. It front-loads the search purpose and criteria, then succinctly states the return content and paging information. Every clause contributes directly to the agent's ability to understand and call the tool.

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?

The description is clear on searchable fields and return format, and the output schema covers the response shape. However, it does not explain that all parameters are optional, how multiple filters combine, or how offset and limit map to paging. For a six-parameter search tool with these constraints, this is a notable gap even if an agent can infer a lot.

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?

The schema covers 50% of parameters with descriptions (city, query, state). The description adds meaning for the model parameter by naming it 'practice model' and reinforces query matching against name, city, doctor, and specialty. However, limit and offset are only implied by 'paging' and are not explicitly described; at 50% schema coverage the description partially compensates but leaves gaps in parameter understanding.

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 description clearly identifies the resource ('Tabflows' DPC Finder directory of direct primary care practices in the US') and the action (search), and enumerates search criteria. It is specific enough to distinguish from a generic search, but it does not explicitly contrast itself with siblings like 'search' or 'get_dpc_practice', so it stops short of full sibling differentiation.

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?

Usage is implied by the description: an agent can infer it is for searching the DPC directory by free text and filters. However, there is no explicit guidance on when to use this instead of 'get_dpc_practice' for a single known practice, nor any statement of when not to use it or requirements like all parameters being optional.

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