ChooseHelp Treatment Directory

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

Annotations already declare readOnlyHint=true, so the description's bar is lower. It adds context that the profile is 'public' and that contact details are intentionally excluded (live on linked page). This gives the agent useful behavioral expectations beyond the annotation without contradiction.

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 main purpose, then a list of profile contents, and a note about contact details. Every word earns its place with zero fluff. Excellent structure for quick scanning.

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 single-parameter tool with an output schema, the description is complete: it lists the main data fields, indicates the source of the username, and states what is NOT included (contact details). The output schema covers return values, so no further explanation is needed. Fully adequate for tool selection and invocation.

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% with 'username' described as 'Expert username from search_experts'. The description repeats this in prose ('by username (as returned by search_experts)') but adds no new semantic detail. Baseline of 3 is appropriate since the schema carries the parameter meaning.

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?

Description clearly states 'Full public profile for one therapist/expert by username' with specific verb 'Get' (from title) and resource. It distinguishes from siblings like search_experts (which returns lists) and get_facility (facilities). Mentions specific fields included (credentials, license type, etc.), so purpose is unambiguous.

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 says username is 'as returned by search_experts', establishing a prerequisite and workflow. It also notes 'Contact details live on the linked profile page', telling the agent when NOT to use this tool (if contact details are needed). This is clear when-to-use vs alternative guidance.

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?

The annotations include readOnlyHint:true, which already signals a safe read operation. The description adds that it returns 'full published details' and that the name parameter accepts partial matches. It does not disclose behavior for ambiguous partial names (e.g., multiple matches) or what happens if the facility is not found, which would be useful additional context.

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 a single sentence of 17 words, front-loaded with the core function ('Full published details for one facility') followed by the two identification methods. No filler or redundant 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?

The tool is simple with an output schema present, so return values are already defined. However, the description does not address important edge cases: what happens if both id and name are provided, or if a partial name matches multiple facilities. These are clear gaps in guidance for an agent, making the description adequate but not fully complete.

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%, meaning both parameters are described in the schema ('Numeric facility id' and 'Facility name, partial match accepted'). The description adds the source hint that id comes from search_facilities, which is a small extra but not substantial. Thus, the description does not significantly expand on 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?

The description clearly states the tool's purpose: retrieving 'Full published details for one facility'. The verb 'get' and resource 'facility' are explicit. It also distinguishes itself from siblings like search_facilities by specifying it returns a single facility, identified by id or name.

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 provides clear usage context: 'by numeric id (from search_facilities)' suggests obtaining an id from the search tool first, and 'or by (partial) facility name' offers an alternative entry point. This gives the agent a clear sense of when to use this tool relative to search_facilities, though it does not explicitly state when not to use it.

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?

Annotations include readOnlyHint=true, so the description doesn't need to repeat safety information. It adds value by detailing the informational content (what each level is, who it suits, facility counts, directory URLs) and its role in the workflow. While it doesn't discuss edge cases or limitations, the tool is a simple read-only lookup, so this is sufficient.

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: the first packs the continuum and the types of information provided; the second gives clear usage guidance. No wasted words, no repetition of schema or annotations, and the information is front-loaded.

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 that there are no parameters and an output schema exists, the description fully covers the tool's purpose, scope, and usage context. It tells the agent exactly what to expect (explanations, suitability, counts, URLs) and when to use it, making it complete for an AI agent to invoke 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?

The input schema has zero parameters, so the baseline is 4. The description appropriately says nothing about parameters, as there are none to explain. Adding parameter-specific details would be redundant.

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 tool explains the substance-use-disorder intensity-of-care continuum, enumerating specific levels (detox, residential, IOP/PHP, outpatient, MAT, sober living). It distinguishes from sibling search/list tools by framing this as an educational resource for understanding treatment options before searching.

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 explicitly says 'Use this to help someone understand which kind of treatment fits before searching,' providing a clear when-to-use directive and implying that search tools are the subsequent step. This effectively differentiates it from the sibling search/list tools.

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?

The readOnlyHint annotation already indicates the tool is safe/read-only. The description adds meaningful behavioral context: the data includes 'live facility counts and URLs' and that values are consumable by search_facilities filters. This goes beyond the annotation and enriches agent understanding without contradiction.

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 concise sentences. The first states the core content and output features (live counts, URLs), the second explains integration with search_facilities. No redundant or irrelevant words; every sentence 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?

For a simple, parameterless list tool with an output schema and readOnly annotation, the description is complete. It explains what the taxonomy is, what categories are included, and how the values are used downstream. The presence of an output schema covers return format details, so no further description is needed.

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, so the baseline score of 4 applies. The description adds no parameter-specific info, but none is needed. It does explain the output semantics, which is appropriate for a parameterless endpoint.

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 tool's purpose: it lists the directory's browse taxonomy (populations and treatment approaches) with live facility counts and URLs. This distinguishes it from sibling list tools like list_facility_types and list_insurers, making the tool's specific scope unambiguous.

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 provides a concrete usage signal: the values returned are accepted by search_facilities' population and approach filters. This implies when to use the tool (to get filter options) but does not explicitly contrast with alternatives like list_facility_types or list_states, so a small deduction applies.

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?

The readOnlyHint annotation already signals a safe read operation. The description adds that the slugs are accepted by search_facilities and that display names and directory URLs are included, providing some useful context. However, it does not disclose additional behavior such as ordering, pagination, or whether the list is static, so it is adequate but not rich.

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 a single, front-loaded sentence that directly states what the tool does. There is zero wasted wording, making it highly concise and readable.

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 parameterless list tool with an output schema and a read-only annotation, the description fully covers the essential information an agent needs: the purpose, content, and relationship to search_facilities. It is complete within its scope.

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, so the description need not explain parameter semantics. The schema coverage is vacuously 100%, and the baseline for no parameters is 4.

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 that the tool lists facility-type slugs accepted by search_facilities, including display names and directory URLs. This is a specific verb-resource pairing that distinguishes it from sibling list tools like list_states or list_insurers.

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?

It implicitly conveys when to use the tool: when you need valid facility-type slugs for the search_facilities tool. It does not explicitly state when not to use it or mention alternatives, but the connection to search_facilities provides clear context.

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?

The readOnlyHint annotation already declares the operation safe; the description adds that results include live facility counts and are limited to providers accepted by published facilities. This extra context goes beyond the annotation without contradicting it.

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 a single, dense sentence that conveys the tool's content and purpose without filler. It front-loads the main point and provides a practical usage note, earning every word.

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?

With an output schema present, return values are structurally documented. The description covers what the list represents and why it exists, which is sufficient for a zero-parameter reference tool. No gaps are apparent.

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 takes no parameters, so the description needn't elaborate on inputs. The schema confirms no parameters exist, and the description's mention of the filter values adds context beyond the empty schema, meeting the baseline for zero-parameter tools.

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 that this tool lists insurance providers accepted by published facilities, and adds that it includes live facility counts. It also frames the output as valid values for search_facilities' insurance filter, which distinguishes it from other list_* tools and clarifies its exact role.

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 explicitly indicates the primary use case: providing valid values for the insurance filter in search_facilities. It doesn't explicitly contrast with sibling tools, but this concrete integration point gives clear when-to-use guidance.

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?

The annotation readOnlyHint=true establishes the safe read nature. The description adds that counts are computed live and include only currently published facilities, which is useful behavioral context beyond the annotation.

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, no filler; front-loads 'All states' and includes the key data points (facility counts, directory URL, live computation). Every phrase 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?

This is a simple no-argument list tool with an output schema available. The description covers the essential return content and the live-count behavior, and the readOnlyHint and output schema handle the rest, making it sufficiently complete.

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, so the description need not add parameter semantics. The schema fully covers with 100% coverage (empty properties), and the baseline for 0 params is 4.

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 title and description clearly state the tool lists all states with counts of currently published facilities and state directory URLs. This distinguishes it from sibling list tools like list_facility_types and list_insurers by resource and included data.

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 does not explicitly state when to use this tool over the sibling search/list tools. However, the scope ('all states') and lack of parameters imply it is for a direct listing task, so usage is implicit rather than clearly guided.

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?

Annotations already declare readOnlyHint=true, so no contradiction. The description adds behavioral detail beyond annotations: results are alphabetical and placement is never paid, plus a safety guideline (share 988). These are valuable but not exhaustive; for example, pagination behavior is not mentioned. Still, it meaningfully supplements the structured metadata.

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 composed of three sentences: a purpose statement, a filtering/ordering note, and a crisis-safety instruction. Each sentence earns its place, but the third sentence is somewhat tangential to tool selection/invocation. It is front-loaded with the core purpose and avoids redundancy.

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 search tool with 5 optional parameters and an output schema, the description covers the domain, filters, ordering behavior, and a safety guideline. It doesn't explicitly address pagination or the online_only parameter, but these are fully detailed in the schema. It could more explicitly contrast with search_facilities, but the title and phrasing deliver enough context.

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 100%, with each parameter already having a clear description (e.g., query matches names, location is substring, specialty is substring). The description only recaps the filter options without adding new semantics, examples, or parameter interactions. Baseline 3 is appropriate given the high schema coverage.

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 uses a specific verb ('Search') and identifies the resource as 'ChooseHelp's licensed therapists, counselors, and addiction specialists,' with the clarifying phrase 'the experts who answer questions on the site.' This clearly distinguishes it from sibling tools like search_facilities and transfers expert- versus facility-focused use cases.

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 provides clear context for when to use the tool: to search experts by name, specialty, or location, and it explains the alphabetical ordering. It doesn't explicitly mention exclusions or alternatives, but the phrasing implicitly separates experts from facilities. It also adds a critical safety directive for crisis situations, which is useful operational guidance.

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?

Beyond the readOnlyHint annotation, the description discloses meaningful behavioral traits: results are neutrally ordered and placement is never paid, and the dataset is curated with independent verification from state-licensing and SAMHSA-derived data. It also adds a critical safety instruction about handling crisis situations, which is highly relevant for this domain.

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 concise yet information-dense. Each sentence earns its place: scope and data source, available filters, neutrality policy, and crisis safety. It front-loads the core action and resource without redundant filler.

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?

Despite having 8 parameters and an output schema, the description adds essential context: data provenance, credibility of the directory, filter capabilities, ordering policy, and a safety protocol. This makes the tool feel complete and well-understood for an AI agent, including domain-specific crisis handling that is crucial for the use case.

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 already provides comprehensive descriptions for all 8 parameters (100% coverage). The description merely lists the filter dimensions in prose without adding syntax, examples, or constraints beyond what the schema states, so it does not significantly elevate parameter understanding above the baseline.

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 tool's purpose: searching ChooseHelp's directory of addiction-treatment and mental-health facilities. It includes specific resource types (rehab centers, detox clinics, etc.) and distinguishes itself from sibling tools like search_experts and get_facility by focusing on facility search.

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 provides clear context about when to use the tool (when searching for facilities) and includes a safety guideline (share 988 first if in crisis). However, it does not explicitly exclude alternatives or contrast with sibling tools like list_facility_types, so it stops short of full differentiation.

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