knack_get_applicationFetch a Knack application's full schema/metadata — its objects (tables), fields, and scenes. Knack API: GET /applications/{app_id}. Returns the raw JSON as-is. app_id defaults to the configured KNACK_APPLICATION_ID.
| Name | Required | Description | Default |
|---|---|---|---|
| appId | No | Optional Knack Application ID; defaults to the configured KNACK_APPLICATION_ID. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, indicating a read-only operation. The description adds that the tool returns the raw JSON as-is, which is valuable for the agent to expect unprocessed data. It also notes the default app_id behavior. 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?
The description is very concise with three sentences. The first sentence immediately states the purpose, the second adds API detail, and the third covers parameter default. 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 only one optional parameter, no output schema, and annotations present, the description is mostly complete. It explains the return format (raw JSON) and the default behavior. It could mention the potential size of the response, but overall it provides sufficient context for an AI 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?
The input schema has 100% coverage with a description for appId that matches the description. The description repeats the defaulting behavior but does not add additional semantic meaning beyond what the schema provides. Baseline score of 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 that the tool fetches the full application schema (objects, fields, scenes). It distinguishes itself from sibling tools like knack_get_record or knack_list_fields by targeting the application-level metadata. The verb 'Fetch' and resource 'application schema' are specific.
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 versus alternatives. While the purpose is clear, there is no guidance on when not to use it or which sibling tool might be more appropriate. The mention of the API endpoint provides technical context but not usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct operation: CRUD for records, listing fields/objects/records, fetching application schema, and a generic request. No overlap in purpose.
All tools use 'knack_' prefix with verb_noun pattern (create_record, delete_record, etc.). The exception is 'knack_request' which lacks a verb, causing slight inconsistency.
9 tools is well-scoped for a Knack integration, covering essential CRUD, listing, schema retrieval, and an escape hatch.
Core CRUD operations are present, plus listing and schema. Missing batch operations or advanced filtering, but the generic request tool fills some gaps.