Список збережених фільтрів/видів таблиці (SearchResult). Дозволяє агенту дізнатись які views вже існують.
| Name | Required | Description | Default |
|---|---|---|---|
| app_id | Yes | Project ID (from list_projects) | |
| entity_id | No | Опційно — фільтр по формі |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds that it lists existing views, which is consistent. No additional behavioral traits (e.g., pagination, ordering) are disclosed, but the bar is lower due to 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?
Two sentences, ~20 words, front-loaded with core functionality. Efficient and to the point with no unnecessary detail.
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 it is a simple list tool with two parameters and annotations, the description is sufficient for an agent to understand its purpose and basic usage. However, it lacks details about return format or pagination, which would enhance completeness.
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% description coverage; both parameters (app_id, entity_id) have descriptions. The tool description does not add further meaning beyond what the schema already 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 that the tool lists saved filters/views for a table (SearchResult) and allows the agent to discover existing views. It is clear and distinguishes from sibling tools like create_saved_view or delete_saved_view, though not explicitly differentiating from other list tools.
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 is provided on when to use this tool versus alternatives or when not to use it. The description only states the basic purpose without context or exclusions.
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 clearly targets a specific resource and action (e.g., create_form vs. delete_form, add_dashboard_item vs. create_calendar). Overlapping functions like delete_few_records and delete_records_by_filter are distinguished by scope. The descriptions provide sufficient detail to avoid confusion.
Most tools follow a verb_noun pattern (create_, delete_, update_, list_, get_). Minor inconsistencies exist (add_ vs create_, set_ for permissions, check_ for status). Overall predictable and readable.
118 tools is unusually large for an MCP server, but each tool addresses a distinct entity or operation within a comprehensive database platform. The count is borderline heavy; while justified by the domain, it may overwhelm agents.
The toolset covers creation, retrieval, updating, deletion, and management for all major entities (projects, forms, fields, records, portals, groups, reports, charts, maps, templates, schedules, etc.). Gaps are minimal (e.g., no duplicate_project), and critical workflows like bulk operations and AI site generation are included.
