Restore a previously deleted knowledge document.
| Name | Required | Description | Default |
|---|---|---|---|
| documentId | Yes | Knowledge document ID |
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | Tool result payload — shape varies per tool, see the tool description | |
| summary | Yes | One-line human-readable summary of the action | |
| renderType | Yes | UI rendering hint for the result |
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 only provide false hints (readOnly, destructive, idempotent), so the description's 'previously deleted' adds context about the operation's nature. However, it does not disclose any behavioral outcomes beyond 'restore' — e.g., whether the document is fully recovered, if versions are preserved, or if permissions are required. No contradiction with 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 a single concise sentence, front-loaded with the action, and contains no extraneous information. It earns its place fully and is appropriately sized for the tool's simplicity.
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 tool with one well-documented parameter and an output schema present, the description is largely sufficient. It doesn't address potential edge cases (e.g., restoring an already-existing doc) but the minimal scope and sibling context make this 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?
The input schema has 100% coverage with documentId described as 'Knowledge document ID'. The description adds no additional meaning beyond the schema, which is acceptable given the high schema coverage. It meets the baseline but does not compensate with extra context about how to obtain the ID or its format.
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 'Restore a previously deleted knowledge document' uses a specific verb ('restore') and specific resource ('knowledge document'), clearly distinguishing it from siblings like delete_knowledge_document and get_knowledge_document. It unambiguously states the tool's purpose.
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 the tool should be used when a knowledge document has been deleted and needs recovery, but it provides no explicit when-to-use guidance, exclusions, or references to alternative tools. There is no mention of prerequisites such as the document being in a trash/archive state.
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.
Many tools have overlapping boundaries, such as generate_post_cover/attach_post_cover_from_job/upload_post_cover_from_url, update_deal/update_deal_stage/mark_deal_won/mark_deal_lost, and booking status transitions (confirm/cancel/complete/mark_no_show). The catch-all execute_tool adds further ambiguity.
Nearly all tools follow a consistent verb_noun snake_case convention (create_*, list_*, get_*, update_*, delete_*, restore_*). Minor exceptions like 'clone' and 'execute_tool' are still readable and do not significantly break the pattern.
With 223 tools, the server is extremely over-scoped. Even for a full CRM platform, this many tools overwhelms context windows and makes tool selection impractical. It far exceeds the reasonable range for an MCP server.
The surface is broad but has notable gaps: no update_booking/delete_booking, no delete_product, no send_message/send_campaign (referenced but absent), and no delete_staff/resource. Some workflows dead-end or require manual approval steps.