Как подключить ПАРСИ к ассистенту — локально (тот же компьютер) или удалённо (с любого устройства). client: claude-code, claude-desktop, kimi, cursor или any.
| Name | Required | Description | Default |
|---|---|---|---|
| client | No | any |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the behavioral disclosure burden. 'How to connect' suggests an instructional/read-only response rather than a state-changing operation, and the local/remote scope is stated. However, it does not disclose prerequisites, whether any configuration changes occur, or what the tool actually returns beyond being a guide.
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 compact and front-loaded: core purpose first, then a terse client-value list. Every sentence earns its place, and there is no repetition of schema details 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?
An output schema exists, so return-shape details are not strictly required in the description. The description covers the purpose and the client parameter well, but it lacks usage boundaries, behavioral caveats, and guidance relative to sibling tools. For a simple one-parameter tool this is close to complete, but the missing safety/behavioral context lowers it.
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 schema provides no description for the 'client' parameter, so the description compensates by enumerating valid values: claude-code, claude-desktop, kimi, cursor, or any. This gives an agent concrete selection guidance. It still does not explain how each client affects the output, but the list is sufficient for basic invocation.
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 goal ('connect PARSEE to the assistant') and distinguishes local vs remote setup scenarios while listing supported clients. It does not explicitly differentiate itself from siblings like parsee_cloud_manual, but 'setup/connect' is specific enough to stand apart.
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?
There is no explicit guidance on when to use this tool versus alternatives. Sibling tools such as parsee_cloud_manual and parsee_help could easily be confused with this one, and the description provides no exclusion criteria or 'use instead' hints.
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.
Most tools map cleanly to distinct resource/action pairs, and the descriptions explicitly point to complementary tools (e.g., browser_search → parse_urls → wait → get_results). The main ambiguity is the help/cloud_manual duplication and the similar price/result output of get_prices versus get_results.
All tools share the parsee_ prefix and snake_case, and most follow a verb_noun pattern (create_group, get_results, set_region). However, several tools are noun-like (status, help, price_history, spp_changes, wb_cabinet) and browser_search reverses the verb_noun order, so the pattern is readable but not uniform.
32 tools is a large surface for an MCP server, even for a broad parsing/monitoring domain. The count feels inflated because multiple cloud/help/documentation tools and several similar data-retrieval tools could be consolidated.
The tool set covers the full workflow: search/discovery, collection, task lifecycle, group management, analytics/history, scheduling, settings, export, and seller-cabinet integration. There are no obvious dead ends, and every operation has the supporting tool needed to act on its output.