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

Annotations already declare read-only, idempotent, non-destructive, and closed-world behavior. The description adds useful context about data source, closest-first straight-line ordering, and returned fields, though it does not discuss rate limits or authentication.

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 front-loaded and dense: first sentence defines scope and search modes, second lists result fields and filters. It is longer than minimal but every part contributes useful selection and result context.

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?

For a read-only search tool with no output schema, the description gives enough: source directory, location modes, level-of-care scope, result contents, and filters. An agent can call it correctly without needing additional return-value documentation.

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 coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema by clarifying ZIP/state/city search modes, one-level-of-care scope, closest-first straight-line distance, and detox/payment filtering. Some parameter detail still overlaps with the schema.

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: find treatment programs in the SAMHSA FindTreatment.gov directory. It clearly specifies search modes (ZIP, state, city) and one level of care, making it distinct from a generic search tool.

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?

Explains the main usage context: search near a ZIP or in a state/city for one level of care, with detox substance and payment filters. It references get_program via result IDs but does not explicitly name state_overview or explain when to choose this over that sibling.

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