cloud_evalStockfish cloud evaluation for a FEN position.
| Name | Required | Description | Default |
|---|---|---|---|
| fen | Yes | FEN of position to evaluate. | |
| multi_pv | No | 1-5 (default 1) |
| Name | Required | Description | Default |
|---|---|---|---|
| fen | No | Position FEN | |
| pvs | No | Principal variations (multi_pv results) | |
| depth | No | Search depth | |
| knodes | No | Kilo-nodes evaluated |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "fen": "rnbqkbnr/pppppppp/8/8/8/8/PPPPPPPP/RNBQKBNR w KQkq - 0 1"
+ },
+ {
+ "fen": "rnbqkbnr/pppppppp/8/8/4P3/8/PPPP1PPP/RNBQKBNR b KQkq e3 0 1",
+ "multi_pv": 3
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "depth": {
+ "description": "Search depth",
+ "type": "number"
+ },
+ "fen": {
+ "description": "Position FEN",
+ "type": "string"
+ },
+ "knodes": {
+ "description": "Kilo-nodes evaluated",
+ "type": "number"
+ },
+ "pvs": {
+ "description": "Principal variations (multi_pv results)",
+ "items": {
+ "properties": {
+ "cp": {
+ "description": "Centipawn evaluation",
+ "type": "number"
+ },
+ "mate": {
+ "description": "Mate in N (if applicable)",
+ "type": "number"
+ },
+ "moves": {
+ "description": "Best line in UCI",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false. The description adds 'cloud evaluation,' hinting at network dependency, but does not disclose details like rate limits, authentication, or error behavior. It does not contradict 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 with no unnecessary words. It is front-loaded with the key verb and resource. While short, it is appropriately sized for a simple tool with rich annotations and schema.
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 low complexity, full parameter descriptions, rich annotations, and existing output schema, the description provides adequate completion. However, it misses potential behavioral context like latency or quota limits for a cloud service.
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 for both parameters (fen and multi_pv). The description does not add extra semantic meaning beyond what is already in the schema, so a baseline 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 the tool performs a Stockfish cloud evaluation on a FEN position. It specifies the verb (evaluation) and resource (FEN position), and differentiates well from sibling tools like opening_explorer or tablebase, though it does not explicitly name them.
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 given on when to use this tool versus alternatives or when not to use it. The description implies usage for chess evaluation but lacks explicit context or exclusion criteria.
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.
The server mixes chess tools with numerous data query tools from Pipeworx, causing significant overlap. Multiple ask_pipeworx variants (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded) and deep_research have similar purposes, making it difficult for an agent to choose correctly. Chess tools are distinct but compete with many unrelated tools.
Tool names follow no consistent pattern: chess tools use mostly underscores (top_players, opening_explorer), Pipeworx tools use mixed styles (ask_pipeworx, deep_research, entity_profile), and memory/subscription tools use simple verbs (remember, subscribe). The naming is inconsistent across the set.
With 41 tools, the count is high and unfocused. A chess server would typically have 10-15 tools; the remaining 31 tools from Pipeworx are unrelated and overwhelm the set. The server tries to cover too many domains, making it bloated for its primary purpose.
The chess-specific tools (10) cover basic queries but lack deeper chess analysis (e.g., puzzles, board evaluation). The extensive Pipeworx tools are out of scope for a Lichess server, resulting in an incomplete surface for the expected domain and an excessive surface for unrelated data lookups.