GTH Intelligence — Substance Abuse Treatment Finder

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

No annotations are provided, so the description must carry the full burden. It fails to disclose what 'detailed information' includes, what happens if no facility matches the name, or whether partial name matching returns the first match, all matches, or an error.

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?

Single, efficient sentence that immediately states the tool's purpose. No redundant words or structural waste.

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?

Given the low complexity (1 parameter with full schema coverage) and absence of an output schema, the description is minimally viable. However, it lacks critical behavioral context about the lookup mechanics and return value structure that would be necessary for robust agent operation.

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 100% schema description coverage, the schema already documents that 'name' accepts 'Full or partial facility name'. The description adds minimal semantic value beyond the schema, merely reinforcing that the name is the lookup key, which warrants the baseline score.

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?

Clear verb ('Get') and resource ('detailed information about a specific treatment facility'). The phrase 'by name' effectively distinguishes this from the sibling 'search_facilities' (which likely supports broader filtering), though it could explicitly state this distinction.

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?

Provides no explicit guidance on when to use this versus 'search_facilities' or other siblings. While 'by name' implies usage when the identifier is known, it does not clarify matching behavior (exact vs. partial) or error handling when multiple facilities match.

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

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

With no annotations provided, the description carries the full burden. It adequately discloses scope ('all' types) and return content type ('definitions and explanations'), but omits details about payload size, caching, or whether this represents a static taxonomy or dynamic data.

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?

Single sentence structure with zero waste. Front-loaded with the action verb 'Get', immediately followed by the resource and value proposition. Every word earns its place.

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?

Given the low complexity (no parameters, simple lookup), the description is appropriately complete. It characterizes the return content (definitions/explanations) even without an output schema, though explicit mention of return format (list vs. object) would be a minor improvement.

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 tool has zero parameters, which per evaluation rules establishes a baseline of 4. The description appropriately requires no parameter explanation since the schema has no properties to document.

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 states the specific action (Get definitions and explanations) and resource (treatment program types). It effectively distinguishes from facility-focused siblings (get_facility_detail, search_facilities) by focusing on program taxonomy rather than locations or specific facilities.

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?

The phrase 'to help users understand their options' provides implied context for when to use the tool (informational/educational scenarios), but lacks explicit guidance on when to prefer this over search_facilities or get_facility_detail.

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

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

With no annotations provided, the description carries the full burden. It successfully discloses key behavioral traits: filtering (only states with 'available' data) and data enrichment (returns 'counts'). However, it omits whether this is a cached/static list, potential rate limits, or the specific nature of the counts (facility counts vs. record counts).

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?

Single sentence with zero waste. The phrase 'with available treatment facility data and counts' is essential for distinguishing this from a simple geographic lookup, earning its place. Information is front-loaded with the verb and subject.

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?

Given the lack of output schema, the description partially compensates by mentioning 'counts' (hinting at return value enrichment), but does not fully describe the return structure, field names, or format. For a zero-parameter discovery tool, this is adequate but not comprehensive.

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 input schema has zero parameters, which per guidelines establishes a baseline of 4. The description correctly implies no filtering parameters are accepted by stating 'List all' without qualification.

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 states the specific action ('List'), resource ('US states'), and crucial scope constraints ('with available treatment facility data and counts'). It effectively distinguishes from siblings like search_facilities or get_facility_detail by focusing on geographic availability discovery rather than specific facility lookup.

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?

While the phrase 'with available treatment facility data' implies this is a discovery tool for finding which states have coverage before searching, it lacks explicit guidance such as 'use this first to identify valid states for search_facilities' or prerequisites for using the tool.

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

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

With no annotations provided, the description carries the full disclosure burden. It successfully compensates for the missing output schema by enumerating return values ('facility names, locations, programs... direct links'), but fails to declare safety properties (read-only vs. destructive), rate limits, or geographic restrictions beyond the implicit 'US state' reference.

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?

Three sentences with zero waste: sentence 1 defines the operation, sentence 2 defines input capabilities, sentence 3 defines output. Information is front-loaded with the core purpose, and every clause earns its place by conveying distinct functional information.

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 5-parameter search tool with no output schema, the description is nearly complete. It compensates for the missing return schema by detailing output fields, and the 100% schema coverage reduces the need for parameter elaboration. Minor gap: does not explicitly note that zero parameters are required or that coverage is US-only.

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 100% schema description coverage, the baseline is appropriately 3. The description mentions four of the five parameters (city, state, treatment_type, insurance) in the context of filtering, but omits 'limit'. It adds no syntax guidance, examples, or constraint explanations beyond what the schema already provides.

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 opens with a clear specific verb ('Search') and distinct resource ('addiction treatment and mental health facilities'). It effectively differentiates from siblings: unlike 'get_facility_detail' (retrieval by ID), 'get_treatment_types' (enumeration), or 'list_states' (geographic listing), this tool is explicitly for filtered discovery.

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?

The description implies usage by listing available filters (state, city, treatment type, insurance), but provides no explicit when-to-use guidance or comparison to siblings. It does not clarify that results from this tool should likely be fed into 'get_facility_detail' for complete information, nor does it state that all parameters are optional.

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