chess_analyze_pgn

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so the description carries full burden. It states analysis with Stockfish and mentions a default time per move (500 ms), but does not disclose what 'analyze' means—e.g., whether it returns evaluations, best moves, or a full analysis report. The return format or side effects are not described. The tool modifies no state, but this is implied rather than stated.

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?

Description is reasonably concise with a parameter list and example. However, it repeats structural elements (parameter list, example) common to many tools. The example uses placeholders ('...'), which could be more specific. The description could be more compact without losing value.

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 has an output schema (likely describing analysis results), the description does not need to detail return values. However, with no annotations and two parameters (one undocumented in schema), the description leaves some gaps: it doesn't explain what constitutes a valid PGN, error handling, or whether the analysis is synchronous. The example helps but is incomplete.

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?

Schema description coverage is 0%, so the description must compensate. It lists parameters: pgn_string (PGN of the game to analyze) and movetime_ms (time per move, default 500). However, it does not specify the format expected for pgn_string (e.g., must be a full PGN with headers? move text only?), nor the valid range or semantics of movetime_ms (e.g., is it milliseconds? does the engine respect it?). The example is helpful but not enough to fully cover undocumented parameters.

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?

Description clearly states 'Analyze a single PGN string with Stockfish', which pairs a specific verb ('analyze') with a resource ('single PGN string'). It distinguishes from siblings like 'chess_analyze_game_id' (analysis from a game ID) and 'chess_analyze_multiple_pgn' (analysis of multiple PGNs). The purpose is clear and 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 implies usage through the example and parameter defaults, but does not explicitly state when to use this tool versus alternatives. For example, it doesn't clarify that this is for a single PGN string, while 'chess_analyze_multiple_pgn' is for multiple. No explicit guidance on excluding other tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.