Sidecar
Server Details
Cross-tool context for your data stack. Search, lineage, and impact across warehouse and BI tools.
- Status
- Unhealthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.3/5 across 10 of 10 tools scored. Lowest: 3.3/5.
There are overlapping tool pairs: advanced_search vs resolve_asset_id (both find assets), calculate_downstream_impact vs inspect_lineage_details (both trace lineage), and describe_asset vs resolve_asset_id (both provide details). While descriptions help clarify distinct use cases, an agent could still be confused about which to call, especially for lineage and asset retrieval.
Nine of ten tools follow a verb_noun pattern (e.g., get_catalog_overview, describe_asset). The exception is 'advanced_search', which uses an adjective instead of a verb, breaking the pattern. This minor inconsistency does not significantly impair usability.
With 10 tools, the server is well-scoped for a data catalog. Each tool serves a distinct purpose in searching, describing, and analyzing data assets and lineage, without being overly numerous or sparse.
The tool set covers core catalog operations: asset search, lookup, detailed descriptions, lineage tracking, downstream impact analysis, and knowledge base access. Minor gaps exist, such as the lack of a full asset listing tool and absence of knowledge base search within files, but these are not critical for typical workflows.
Available Tools
10 toolsadvanced_searchAInspect
Search for data assets using identifier matching, keyword search, semantic similarity, or hybrid fusion.
Use 'identifier' mode (default) when you know the asset name or a pattern (supports * wildcards). Use 'keyword' when searching by domain terms or metadata keywords. Use 'semantic' for natural language queries about what the data represents. Use 'hybrid' to combine all approaches for the best recall.
Returns a ranked list of matching assets with identifiers, types, and relevance scores.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Search mode. 'identifier' (default): exact/wildcard match on asset_identifier. 'keyword': full-text search over indexed keywords. 'semantic': vector similarity search. 'hybrid': fuses identifier + keyword + semantic results via RRF. | identifier |
| tags | No | Filter to assets with any of these tags (OR semantics). | |
| limit | No | Maximum number of results (1-50). | |
| query | Yes | Search query. For identifier mode: asset name or wildcard pattern (e.g. 'fct_orders', 'stg_*', 'analytics.*customers'). For keyword/semantic/hybrid: natural language query (e.g. 'revenue metrics', 'user activity tracking'). | |
| tool_type | No | Filter to a specific tool. UPPERCASE, e.g. SNOWFLAKE, DBT_CLOUD, BIGQUERY. | |
| asset_type | No | Filter to a specific asset type. snake_case, e.g. snowflake_table, dbt_model. | |
| importance | No | Filter to a specific importance level: 'high', 'medium', or 'low'. |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully carries the burden. It discloses the search behavior (exact, full-text, vector, fused via RRF), filtering capabilities, and return format (ranked list with identifiers, types, relevance scores). No behavioral surprises.
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 longer than ideal but well-structured: a one-sentence summary, followed by a bullet list of mode usage, then note on return format. Information is front-loaded and relevant. Could be slightly tighter but still effective.
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 (7 parameters, output schema exists but not shown), the description covers all necessary aspects: modes, filters, return values. It provides enough context for an agent to use the tool correctly without additional information.
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 baseline is 3. The description adds value beyond the schema by explaining modes in more detail, providing example queries, clarifying OR semantics for tags, and noting acceptable formats. This elevates the score to 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 uses a specific verb ('Search') and identifies the resource ('data assets'). It clearly outlines four distinct modes (identifier, keyword, semantic, hybrid), which differentiates it from sibling tools that are not search-focused.
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 tells when to use each mode ('Use...when...'), providing clear guidance on context. It also notes the default mode, helping the agent decide. No sibling tool performs similar search, so no alternatives need to be excluded.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
calculate_downstream_impactAInspect
Find everything downstream of a data asset — tables, dashboards, and reports that would break or be affected if this asset changes.
Call this automatically after the user modifies any SQL file, dbt model, or source definition, or whenever they ask 'what depends on X?' or 'what breaks if I change Y?'
Returns a breakdown of affected assets by tool type and a full list of downstream nodes.
| Name | Required | Description | Default |
|---|---|---|---|
| max_depth | No | Downstream depth to traverse for impact analysis. | |
| tool_type | No | Optional tool/source hint (e.g., DBT_CLOUD, SNOWFLAKE). | |
| asset_identifier | Yes | Asset name or Sidecar asset identifier to analyze (e.g., 'fct_reviews' or 'model.jaffle_shop.fct_reviews'). |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool returns a breakdown of affected assets by tool type and a full list of downstream nodes, and implies it is a read-only analysis by stating it finds what would break. However, it does not explicitly mention read-only behavior, authentication needs, or potential limits like pagination, but the context is relatively transparent.
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 three sentences, front-loaded with purpose, followed by usage triggers and return format. Every sentence adds value with no redundancy or fluff. 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?
The description covers the essential context: purpose, when to use, and what is returned. An output schema exists, so return value details are not needed. However, it could mention that the tool is read-only or any prerequisites, but overall it is sufficiently complete for effective use.
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%, so the input schema already explains all parameters with descriptions. The tool description does not add new meaning or usage hints beyond the schema, such as how to use 'max_depth' or 'tool_type' effectively. Baseline 3 is appropriate.
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 finds everything downstream of a data asset, specifically tables, dashboards, and reports that would break or be affected. It uses a specific verb ('find') and resource, and distinguishes from sibling tools like 'get_column_lineage' by focusing on downstream impact and breakage.
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 states when to call the tool: automatically after modifying SQL files, dbt models, or source definitions, or when the user asks about dependencies or breakage. This provides clear context and triggers, making it easy for an agent to decide when to invoke it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
describe_assetAInspect
Fetch detailed information about a data asset by its identifier.
Resolves the asset, then fetches the requested sections in parallel. Use this after advanced_search or resolve_asset_id to get deeper information about a specific asset.
Sections:
overview: asset description, importance, owner, metadata
columns: full column schema with types and descriptions
tests: dbt test coverage (only for assets with a dbt parent)
context_counts: cheap count of linked tickets and Slack threads
tickets: full Jira/Linear ticket content
slack: full Slack thread content (truncated to first 5 messages per thread)
| Name | Required | Description | Default |
|---|---|---|---|
| include | Yes | Which sections to fetch. One or more of: 'overview' (description, importance, owner), 'columns' (schema), 'tests' (dbt test coverage), 'context_counts' (ticket/slack counts), 'tickets' (full ticket content), 'slack' (full slack thread content). Pick only what you need to keep payloads small. | |
| tool_type | No | Optional tool/source hint to disambiguate (e.g. SNOWFLAKE, DBT_CLOUD). | |
| asset_identifier | Yes | Asset name or Sidecar asset identifier (e.g. 'fct_orders' or 'model.jaffle_shop.fct_orders'). |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Describes parallelism ('fetches the requested sections in parallel') and truncation behavior for Slack threads ('truncated to first 5 messages'). No annotations exist, so description carries full burden; it adds value beyond schema without contradicting any annotations.
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 bullet points for sections, each sentence is purposeful, and it front-loads the purpose. No extraneous text; every part 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 output schema exists (context signal indicates true), description need not explain return values. It covers tool purpose, when to use, sections, and parallel fetching. Complete for a detailed info-fetching tool.
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%, baseline 3. Description adds meaning by detailing each section (e.g., 'columns: full column schema with types and descriptions') and clarifying asset_identifier examples. This goes beyond schema descriptions, enhancing understanding.
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 'Fetch detailed information about a data asset by its identifier', providing a specific verb and resource. It lists sections and contents, and distinguishes from siblings by advising use after 'advanced_search' or 'resolve_asset_id'.
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 'Use this after advanced_search or resolve_asset_id to get deeper information about a specific asset' and advises picking only needed sections to keep payloads small. Lacks explicit when-not scenarios but provides clear usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_catalog_overviewAInspect
Get a summary of everything available in this customer's Sidecar catalog.
Returns the connected tools (e.g. SNOWFLAKE, DBT_CLOUD, LOOKER), asset type breakdown with counts, all available tag names, and a customer-provided company summary describing the company's domain and data landscape (if set).
Call this at the start of any open-ended exploration (e.g. 'what data do we have?', 'show me all Snowflake tables'), or when a search returns no results and you need to understand what's actually in the catalog before trying again. Use the customer_summary field (when present) to understand the business context behind the data.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It explains return value and suggests usage patterns. It does not discuss performance or rate limits, but for a simple read operation this is acceptable. No contradictions.
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?
Four sentences, front-loaded with purpose. Every sentence adds value without redundancy. Efficient and well-organized.
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 zero parameters and no annotations, description provides comprehensive context: return values, usage timing, and guidance for interpreting the customer_summary. Output schema exists to formalize return structure.
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?
No parameters exist, baseline is 4. Description adds no param details (not needed). Schema coverage is 100% by absence.
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 retrieves a summary of the Sidecar catalog, listing specific return components (connected tools, asset counts, tags, company summary). It contrasts with sibling tools by offering a broad overview rather than specific searches or lineage.
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 recommends calling at the start of open-ended exploration or after failed searches. Provides examples ('what data do we have?') and advises using customer_summary for business context. Clearly distinguishes from alternatives like advanced_search.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_column_lineageAInspect
Trace column-level lineage — which upstream columns feed into a column and which downstream columns consume it.
Use this when the user asks 'where does this column come from?', 'what columns feed into X.col?', or needs to understand column-level data flow.
Returns the target column, upstream columns (with levels), and downstream columns (with levels).
| Name | Required | Description | Default |
|---|---|---|---|
| tool_type | No | Optional tool/source hint (e.g., DBT_CLOUD, SNOWFLAKE) to disambiguate when multiple assets share the same identifier. | |
| column_name | Yes | The column name to trace lineage for (case-insensitive). | |
| upstream_depth | No | Levels of upstream column lineage to include. | |
| asset_identifier | Yes | Asset name or Sidecar asset identifier (e.g., 'fct_orders' or 'model.jaffle_shop.fct_orders'). | |
| downstream_depth | No | Levels of downstream column lineage to include. |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It describes the return format (target, upstream, downstream columns with levels) but does not mention side effects, authorization needs, or read-only nature. This is adequate but not fully transparent.
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 three sentences long, front-loaded with the core purpose, followed by usage guidance and a summary of return content. Every sentence adds value without 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?
Given the tool has 5 parameters (2 required) and an output schema exists, the description provides a good high-level explanation. It covers purpose, usage, and return structure. It could be slightly more specific about edge cases or parameter interactions, but overall it is complete enough.
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. The description adds minimal extra beyond schema parameter descriptions, such as contextualizing 'upstream' and 'downstream' with levels. It does not significantly enhance understanding of individual parameters.
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 traces column-level lineage, specifying both upstream and downstream directions. It uses specific verbs ('trace') and resources ('column-level lineage'), and the context of sibling tools like 'inspect_lineage_details' suggests differentiation at a different granularity.
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 explicit example queries ('where does this column come from?') and states when to use the tool. It does not explicitly mention alternatives or when not to use, but the guidance is clear and contextually sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_context_repoBInspect
Return the clean OSI semantic contract currently deployed to this MCP token's Context Garage surface.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It merely states the return action without disclosing side effects, authentication needs, or rate limits. Minimal behavioral 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 a single sentence, front-loaded with the action and object. It is concise but uses domain-specific jargon ('clean OSI semantic contract') that may require additional clarification.
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 retrieval tool with no parameters and an output schema, the description is adequate but lacks context about what the 'clean OSI semantic contract' is and how it differs from similar tools like get_catalog_overview.
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?
No parameters exist; baseline score of 4 applies. The description does not need to add parameter information.
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 action (Return) and the resource (clean OSI semantic contract). It is specific and distinguishes from sibling tools like advanced_search and describe_asset, though not explicitly.
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?
No guidance on when to use this tool versus alternatives. No mention of prerequisites, exclusions, or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_knowledge_base_file_contentAInspect
Fetch the full text content of a file from the customer's knowledge base.
Use this after calling list_knowledge_base_files to get file IDs. Works with any file in the knowledge base — playbooks, metric definitions, nuances, or captured context summaries.
| Name | Required | Description | Default |
|---|---|---|---|
| file_id | Yes | UUID of the knowledge base file to retrieve. Get file IDs from list_knowledge_base_files. |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does not disclose any additional behavioral traits (e.g., read-only nature, authentication needs, size limits) beyond what is obvious from the name and purpose. The behavior is straightforward but could be more explicit.
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 well-structured sentences, no wasted words, front-loaded with the primary action. Very concise and easy to parse.
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 has one parameter, an output schema (exists but not shown), and simple behavior, the description provides sufficient context. It could mention output format, but the output schema likely covers that. Nearly 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?
Input schema has 100% coverage and describes the parameter. The description does not add significant extra meaning beyond 'get file IDs from list_knowledge_base_files', which is already in the schema description. Baseline score for high 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 clearly states the tool fetches the full text content of a knowledge base file, using a specific verb and resource. It distinguishes itself from the sibling 'list_knowledge_base_files' by implying content retrieval vs listing.
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 to use after 'list_knowledge_base_files' to get file IDs, and notes it works with any file type in the knowledge base. No direct mention of when not to use, but the context is clear enough for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
inspect_lineage_detailsAInspect
Trace the full data lineage for an asset — both upstream sources and downstream consumers.
Use this when the user asks 'where does this data come from?', 'what feeds into X?',
or needs the raw lineage graph. For pure downstream impact (blast radius), prefer
calculate_downstream_impact instead.
| Name | Required | Description | Default |
|---|---|---|---|
| tool_type | No | Optional tool/source hint (e.g., DBT_CLOUD, DBT_CORE). | |
| upstream_depth | No | Levels of upstream lineage to include. | |
| asset_identifier | Yes | Asset name or Sidecar asset identifier to trace (e.g., 'fct_reviews' or 'model.jaffle_shop.fct_reviews'). | |
| downstream_depth | No | Levels of downstream lineage to include. |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions tracing both upstream and downstream and returns a raw lineage graph, but does not disclose behavioral traits such as whether it is read-only, performance implications, authentication requirements, or what the response contains beyond the graph. The output schema exists, which helps, but behavioral details beyond the schema are lacking.
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 (about 60 words) and front-loaded with the main purpose in the first sentence. Every sentence adds value: main purpose, usage examples, and sibling distinction. 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?
Given the complexity of lineage tracing, 4 parameters, and the presence of an output schema, the description is complete. It clearly states what the tool does, when to use it, and how it differs from a sibling. The output schema handles return value documentation, so the description does not need to explain that.
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%, meaning all parameters have descriptions in the schema. The description itself does not add meaning beyond what the schema already provides, so the baseline of 3 is appropriate. The description does not describe parameter syntax or constraints beyond what the schema offers.
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 traces full data lineage (upstream and downstream), using specific verbs like 'Trace' and naming the resource 'data lineage for an asset'. It distinguishes from the sibling tool `calculate_downstream_impact` by specifying that this tool provides the raw lineage graph, while that one is for pure downstream impact.
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 provides usage context: use when user asks 'where does this data come from?' or 'what feeds into X?', or needs the raw lineage graph. It also gives an explicit exclusion: for pure downstream impact (blast radius), prefer `calculate_downstream_impact` instead.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_knowledge_base_filesAInspect
List all files in the customer's knowledge base.
The knowledge base contains company-specific reference material — playbooks, metric definitions, business nuances, and conventions — uploaded by the customer's team.
Returns file names, paths, types, and IDs. Pass a file ID to get_knowledge_base_file_content
to read its content. Use the optional folder_path parameter to narrow results to a specific folder.
| Name | Required | Description | Default |
|---|---|---|---|
| folder_path | No | Optional folder path to filter results (e.g. '/Playbooks', '/Metrics and Drivers'). When omitted, returns all files across the entire knowledge base. |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries the full burden. It discloses return values (file names, paths, types, IDs) but does not mention pagination, result limits, or any potential destructive behavior. It implies a read-only operation. The disclosure is adequate but could be more complete.
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 fairly concise with three short paragraphs. The first sentence is clear and front-loaded. The second paragraph adds context about the knowledge base content, which is helpful but slightly redundant given the tool name. Overall, no unnecessary sentences.
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 (one optional parameter, output schema exists), the description is quite complete. It explains the tool's purpose, what it returns, how to narrow results, and the next step (using get_knowledge_base_file_content). It doesn't mention sorting or pagination, but for a simple list tool this is acceptable.
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 the single parameter, but the description adds value by providing examples ('/Playbooks', '/Metrics and Drivers') and clarifying that omitting it returns all files. This goes beyond the schema's generic description.
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 lists all files in the knowledge base, using a specific verb ('List') and resource. It distinguishes itself from the sibling tool 'get_knowledge_base_file_content' by mentioning that the latter reads file content.
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 explains when to use this tool (to list files) and provides guidance to use 'get_knowledge_base_file_content' to read content. It also mentions the optional folder_path parameter for narrowing results. However, it does not explicitly state when not to use it compared to other sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
resolve_asset_idAInspect
Look up any data asset by name across the full catalog (dbt, Snowflake, BigQuery, Looker, etc.).
Returns the asset's columns, description, owner, tags, and its Sidecar asset identifier
(asset_identifier field) — the fully-qualified internal name used by lineage and impact tools
(e.g. model.jaffle_shop.fct_orders, PROD_DB.ANALYTICS.FCT_ORDERS).
When a single asset is resolved, the response also includes a context_summary with
counts of linked tickets (Jira/Linear) and Slack threads. If those counts are non-zero
and relevant to the user's question, follow up with describe_asset using
include=['tickets'] or include=['slack'] to fetch the actual content.
Call this first whenever the user refers to a specific table, model, view, or dashboard.
| Name | Required | Description | Default |
|---|---|---|---|
| tool_type | No | Narrow to a specific tool. UPPERCASE, e.g. SNOWFLAKE, DBT_CLOUD, DBT_CORE, BIGQUERY, LOOKER, METABASE, FIVETRAN, POWER_BI, REDSHIFT. Call get_catalog_overview to see which tools are connected for this customer. | |
| asset_name | Yes | Name or query for the asset to look up. Plain name ('fct_reviews'), wildcard ('fct_*'), or filters inline ('fct_reviews tool_type:SNOWFLAKE', 'tag:finance'). Filter keys: tool_type (UPPERCASE, e.g. SNOWFLAKE, DBT_CLOUD, BIGQUERY), asset_type (snake_case, e.g. snowflake_table, dbt_model), tag (exact tag name). Call get_catalog_overview to see all valid values for this customer. | |
| asset_type | No | Narrow to a specific asset type. snake_case, e.g. snowflake_table, dbt_model, dbt_source, looker_dashboard. Call get_catalog_overview to see all asset types present for this customer. |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Describes return fields (columns, description, owner, tags, asset_identifier, context_summary) and implies read-only operation. Lacks details on edge cases like multiple matches, but transparency is high given no annotations.
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?
Well-structured with main action front-loaded. Every sentence serves a purpose, no redundancy. Length is appropriate for the complexity.
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?
Covers purpose, usage guidance, return contents, and connection to sibling tools. With an output schema present, the description does not need to detail return format further.
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%, but the description adds value by explaining wildcard usage and inline filters in asset_name, and references to get_catalog_overview. This goes beyond schema descriptions.
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: 'Look up any data asset by name across the full catalog' and lists specific return fields. It differentiates from siblings by advising to call this first for specific assets.
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 instructs: 'Call this first whenever the user refers to a specific table, model, view, or dashboard.' Also provides guidance on follow-up with describe_asset based on context_summary counts.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!