Browse published Bible verse collections for memorization — multilingual, free, spaced repetition
Scored across 3 tools
Each tool serves a distinct purpose: browsing/searches, retrieving full details, and viewing engagement metrics. No overlap in functionality.
All tool names follow a consistent verb_noun pattern: browse_collections, get_collection_detail, get_collection_metrics. The pattern is uniform and predictable.
With 3 tools, the server is well-scoped for a read-only collection browsing and metrics use case. Each tool earns its place, and the count is within the typical 3-15 range.
The read-side coverage (browse, detail, metrics) is solid, but there are no create, update, or delete operations, and the get_collection_detail description mentions create_collection/add_verse tools that are not present. This suggests notable gaps in the expected lifecycle coverage.
Browse published Bible verse collections. Search by keyword, filter by language, sort by popularity.
Each result includes the collection's raw cover image — the URL the publisher
set, or null if they set none (the app may still show an auto-generated cover when
null). This is the stored value, not the computed display image.
Args: search: Search term to filter by name, description, or publisher name. language: Language code prefix (e.g. "en", "de", "ja", "zh"). ordering: Sort order: -downloads (default), -created, name. limit: Number of results (1-100, default 20). offset: Starting position for pagination.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| offset | No | ||
| search | No | ||
| language | No | ||
| ordering | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (readOnly, idempotent, non-destructive), the description reveals the nuanced behavior of the 'image' field: it returns the raw stored URL, may be null, and is not the computed display image. This adds valuable extra context that annotations alone don't provide.
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 with the core purpose and then provides a cleanly structured Args section. Every sentence adds necessary detail (image nuance, parameter semantics) without fluff, making it appropriately concise for such a rich 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?
Given the tool's complexity (5 parameters, pagination, sorting), the description covers all operational aspects. It explains parameter semantics, image behavior, and default values. An output schema exists, so not detailing return values is fine, making the description complete for an agent to select and 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?
With 0% schema coverage, the description fully compensates by explaining every parameter: search targets name/description/publisher, language is a code prefix, ordering lists valid options with defaults, and limit/offset have ranges and defaults. This is far more than the bare schema 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 clearly states the tool browses published Bible verse collections with search, filter, and sort capabilities. It uses a specific verb ('browse') and resource ('collections'), and distincts from siblings (detail and metrics) by focusing on list/search behavior.
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 this tool: to browse/search collections with filtering and pagination. It doesn't explicitly exclude alternatives or name sibling tools, but the context is unambiguous given the sibling names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get full details of a published collection including all verse text, references, and topics.
The collection and each verse include a raw image — the URL stored by the
publisher, or null if none was set (the app may still display an auto-generated
cover when null). These are the stored values, not the computed display image, and
round-trip with create_collection / add_verse if you copy this collection.
Args: collection_id: The collection ID (from browse_collections results).
| Name | Required | Description | Default |
|---|---|---|---|
| collection_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, so the bar is lower. The description adds valuable behavioral context: the image field is the raw stored URL (not the computed display), may be null, and 'round-trip[s] with create_collection / add_verse.' It also narrows applicability to 'published collection.'
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 well-structured with a clear summary, a focused paragraph on image behavior, and an Args section. It is slightly verbose for a simple getter, but each sentence serves a purpose—especially the image caveat.
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, the description needn't explain return format. It covers what is returned (verse text, references, topics), the image nuance, and the ID source. Combined with rich annotations, this gives a complete picture for an agent.
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 0%, so the description must compensate. It fully explains the only parameter: 'collection_id: The collection ID (from browse_collections results),' providing both meaning and source. This is sufficient for a single integer parameter.
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 'Get' with the resource 'published collection' and explicitly states the scope: 'all verse text, references, and topics.' This clearly distinguishes it from sibling tools like browse_collections (list) and get_collection_metrics (metrics).
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 communicates when to use this tool by stating the collection_id comes 'from browse_collections results,' implying a workflow. It also mentions round-tripping with create_collection/add_verse for copying. However, it does not explicitly contrast with get_collection_metrics or 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.
Get community engagement metrics: memorization progress, verse mastery, difficult verses, and activity stats.
Args: collection_id: The collection ID (from browse_collections results).
| Name | Required | Description | Default |
|---|---|---|---|
| collection_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the operation as read-only, idempotent, and non-destructive. The description adds a list of metric types, which is helpful for understanding the scope of return data, but it does not disclose behavioral nuances like permissions, rate limits, or side effects. It is not contradictory to annotations, but offers limited additive insight.
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 extremely concise: one summary sentence listing the metrics and one parameter explanation. It is front-loaded with the core purpose and contains no unnecessary words or 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?
For a tool with a single parameter, strong annotations (read-only, idempotent), and an output schema, the description covers the essential context. It clearly explains what the tool does, what metrics are included, and how to obtain the parameter value, making it fully sufficient for an 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 only specifies collection_id as an integer with no description. The description compensates fully by stating 'The collection ID (from browse_collections results)', which tells the agent exactly where to obtain a valid value. With 0% schema coverage, this parameter explanation is essential and highly valuable.
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 with a specific verb ('get') and resource ('community engagement metrics'), and enumerates concrete metric categories (memorization progress, verse mastery, difficult verses, activity stats). This unambiguously distinguishes it from sibling tools like browse_collections and get_collection_detail.
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 gives a direct guideline for obtaining the collection_id ('from browse_collections results'), which establishes a prerequisite and a usage sequence. However, it does not explicitly contrast with get_collection_detail or state when not to use this tool, so it misses the opportunity for full usage clarity.
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.
get_daily_readingget_daily_readingcreate_collectiondelete_collectionupdate_collectionupdate_versedelete_collectionupdate_collectionupdate_versecreate_collectionbrowse_collectionsget_collection_detailget_collection_metrics
Add one secure layer between your agents and this server.