Clinician-reviewed library on child psychiatric evaluation and medication decision-making.
Scored across 6 tools
Each tool targets a distinct action: retrieving full articles, listing, searching, citing, fetching site info, and surfacing crisis resources. There is no meaningful overlap between any two tools, and the descriptions make selection unambiguous.
All tool names follow a consistent verb_noun pattern in snake_case: cite_article, get_article, get_crisis_resources, get_microsite_info, list_articles, search_articles. The naming style is uniform and predictable.
Six tools is well-scoped for an article library server. Each tool serves a necessary function without redundancy, covering discovery, retrieval, citation, contextual metadata, and a safety resource.
The tool surface covers the full read-side lifecycle for an editorial article library: search, list, get, and cite. Since this is a public content resource rather than a CMS, write operations are not expected, and no obvious dead ends remain for typical agent workflows.
Get a formatted citation for a Psychiatry for Children article. Supports AMA, APA, and Chicago styles.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Article slug. | |
| format | No | Citation style (default ama). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true, covering the safety profile. The description adds that it supports AMA, APA, and Chicago styles and defaults to AMA, though this is also in the schema enum. No further behavioral traits like error handling or rate limits are disclosed, but the tool is simple and read-only.
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 concise sentence with the verb and resource front-loaded. It contains no filler or redundant information, making it highly efficient.
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 2-parameter, read-only citation tool, the description, schema, and annotations are sufficient. It clearly states the output ('formatted citation') and supported styles. A small gap exists around error behavior or return format specifics, but these are minor for a tool of this simplicity.
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 clear descriptions for 'slug' and 'format' (including the default). The description does not add additional parameter meaning beyond what the schema already provides, so the baseline score of 3 applies.
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 uses a specific verb 'Get a formatted citation' and specifies the resource 'Psychiatry for Children article'. This clearly distinguishes it from sibling tools like get_article (content retrieval) and search_articles (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 makes the use case clear (produce a citation) but does not explicitly state when to use this tool over alternatives or mention exclusions. The context 'formatted citation' strongly implies when to use it, so it earns a 4 rather than a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch a single article from Psychiatry for Children by slug. Returns title, body content, author, clinical reviewer, citations, and metadata.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Article slug. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotation readOnlyHint=true already signals a safe read operation. The description adds value by disclosing the exact return fields (title, body, author, clinical reviewer, citations, metadata), which goes beyond the annotation and gives the agent a concrete expectation of the response.
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, front-loaded with the action and resource, and lists return contents without any filler. Every sentence contributes meaningful information, making it highly efficient.
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 one-parameter, read-only tool with no output schema, the description fully covers the purpose, the parameter, and the return contents. It gives the agent everything needed to call and interpret the tool correctly, without unnecessary details.
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 the 'slug' parameter already described as 'Article slug.' The description only reinforces 'by slug' without adding deeper semantic detail, such as format or uniqueness constraints. The baseline of 3 is appropriate since the schema does the heavy lifting.
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 the specific verb 'Fetch' and identifies the resource as 'a single article from Psychiatry for Children by slug.' This clearly differentiates it from siblings like list_articles and search_articles, which handle multiple or filtered articles.
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 makes the context clear: use when you need a specific article by slug. While it doesn't explicitly mention alternatives or exclusions, the 'by slug' phrasing implies the usage scenario. It lacks an explicit 'use list_articles for multiple' note but is otherwise clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the canonical 988 / 911 / Crisis Text Line payload. Surface this immediately whenever the user signals self-harm or imminent danger.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint: true. The description adds that the payload is 'canonical' and suggests it should be surfaced with urgency, which is useful behavioral context beyond the annotation. No contradictions with the read-only 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 redundant words. The first sentence states the function and the second gives usage guidance. Perfectly sized and 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?
For a tool with no parameters, no output schema, and a straightforward read-only action, the description fully covers its purpose, usage trigger, and distinguishes it from all siblings. It is 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 baseline is 4. The description mentions no parameters, but none exist to document, so no additional value is needed.
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 a specific verb ('Return') and resource ('canonical 988 / 911 / Crisis Text Line payload'). It distinguishes itself from siblings that handle articles/microsite info, making the purpose 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 states when to use: 'immediately whenever the user signals self-harm or imminent danger.' This is a clear trigger condition. Since no alternative tool exists for this purpose (siblings are about articles), no exclusions are necessary.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Identity and links for Psychiatry for Children: tagline, audience, focus, publisher, sponsor relationship to Emora Health, and key URLs.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already covers the safety profile, and the description adds useful content context by enumerating the specific fields returned (tagline, audience, sponsor relationship, etc.). It does not disclose additional behavioral traits such as response format or error behavior, but for a simple read-only tool with no parameters, this is acceptable.
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, focused sentence that lists the key content items without any filler. It is front-loaded with the core purpose and well-structured for quick agent parsing.
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 tool's simplicity (0 params, read-only, no output schema), the description is fully complete for the agent's needs. It clearly states what information is available, and sibling tools cover other distinct contexts.
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 input schema fully covers parameter semantics. The description appropriately does not need to elaborate on parameters, 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 description clearly identifies the resource (Psychiatry for Children) and the specific information scope (tagline, audience, focus, publisher, sponsor relationship, URLs), distinguishing it from sibling article tools. However, it lacks an explicit verb like 'returns' or 'provides', making the purpose slightly less direct than a fully verb-led description.
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 this tool is for retrieving microsite metadata and links, but it does not explicitly state when to use this tool versus alternatives. Sibling tool names suggest article- and crisis-related use cases, yet the description offers no direct guidance or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Paginated list of articles from Psychiatry for Children. Returns title, slug, summary, and URL.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page number (1-indexed). | |
| limit | No | Max results per page (default 30, max 100). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true, and the description adds useful behavioral context: results are paginated and include title, slug, summary, and URL. However, it doesn't disclose additional traits such as default pagination limits, ordering, or potential performance considerations, though the schema does document limits.
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 efficiently states the purpose, source, and return fields. Every word earns its place, with no redundant or filler content.
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 read-only list operation with two fully documented optional parameters and no output schema, the description adequately covers source, pagination, and return fields. It could mention ordering or default limit behavior, but the schema already supplies defaults, so the description is reasonably 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 input schema already has 100% coverage with clear descriptions for both page (1-indexed) and limit (default 30, max 100). The description only adds the word 'paginated', which is already evident from the parameters, providing no additional semantic value beyond 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 verb 'list', the resource 'articles from Psychiatry for Children', and scope as a paginated list with specific return fields. This distinguishes it from sibling tools like get_article (single item) and search_articles (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 implies use for browsing or retrieving all articles in a paginated manner, but it does not explicitly mention when to use this tool over alternatives like search_articles or get_article. No exclusions or alternative tool names are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Psychiatry for Children's editorial corpus by query. Returns title, slug, summary, and URL for matching articles.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Alternate parameter name for `query`. | |
| limit | No | Max results (default 10, max 50). | |
| query | Yes | Free-text search query. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true, and the description adds context by specifying the corpus scope and return format. No contradictions or additional behavioral notes (e.g., auth, rate limits) are present, but the read-only nature is clearly implied.
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 efficiently states the action, target, and return fields without wasted words.
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 search tool with well-documented parameters and no output schema, the description lists the return fields, making it complete enough for an agent. Minor gaps like pagination or default limits are covered by the schema.
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% for all parameters (query, q, limit), and the description adds no extra meaning beyond 'by query.' The schema fully documents parameter details, so the description provides no additional value.
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 searches a specific corpus ('Psychiatry for Children's editorial corpus') and lists the return fields (title, slug, summary, URL). This distinguishes it from sibling tools like list_articles or get_article.
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 (search by query) but does not explicitly state when to use this tool over alternatives or mention any exclusions. Sibling tools exist for listing or fetching specific articles, but no guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
cite_article1 field changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"get_article1 field changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"get_crisis_resources1 field changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"get_microsite_info1 field changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"list_articles1 field changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"search_articles1 field changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"cite_article2 fields changedInput schema / $schemaAdded value: +"http://json-schema.org/draft-07/schema#"Input schema / properties / format / descriptionPrevious value: -"Citation format. Default: ama."New value: +"Citation style (default ama)."get_article2 fields changedInput schema / $schemaAdded value: +"http://json-schema.org/draft-07/schema#"Input schema / properties / slug / descriptionPrevious value: -"Article slug, e.g. \"what-an-evaluation-actually-looks-like\"."New value: +"Article slug."get_crisis_resources1 field changedInput schema / $schemaAdded value: +"http://json-schema.org/draft-07/schema#"get_microsite_info1 field changedInput schema / $schemaAdded value: +"http://json-schema.org/draft-07/schema#"list_articles9 fields changedInput schema / $schemaAdded value: +"http://json-schema.org/draft-07/schema#"Input schema / properties / limit / descriptionPrevious value: -"Page size (default 30, max 100)."New value: +"Max results per page (default 30, max 100)."Input schema / properties / limit / maximumAdded value: +100Input schema / properties / limit / minimumAdded value: +1Input schema / properties / limit / typePrevious value: -"number"New value: +"integer"Input schema / properties / page / descriptionPrevious value: -"Page number (default 1)."New value: +"Page number (1-indexed)."Input schema / properties / page / maximumAdded value: +9007199254740991Input schema / properties / page / minimumAdded value: +1Input schema / properties / page / typePrevious value: -"number"New value: +"integer"search_articles6 fields changedInput schema / $schemaAdded value: +"http://json-schema.org/draft-07/schema#"Input schema / properties / limit / maximumAdded value: +50Input schema / properties / limit / minimumAdded value: +1Input schema / properties / limit / typePrevious value: -"number"New value: +"integer"Input schema / properties / qAdded value: +{
+ "description": "Alternate parameter name for `query`.",
+ "type": "string"
+}Input schema / properties / query / descriptionPrevious value: -"Free-text query. Matches title and summary."New value: +"Free-text search query."cite_articleget_articleget_crisis_resourcesget_microsite_infolist_articlessearch_articlesPlain-English child psychiatry library — short explainers and decision guides for parents.
Adolescent psychiatry library focused on the medication decisions parents wrestle with.
Clinician-reviewed library on ADHD in children — evaluation, treatment, school, parenting.
Clinician-reviewed library on ADHD in teens — accommodations, executive function, evaluations.
Add one secure layer between your agents and this server.
