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

With no annotations, the description carries the full burden. It discloses the tool's output: per-move classification, win% before/after, centipawn loss, engine's preferred move, tactical-motif tags, per-side accuracy/ACPL, per-phase breakdown, and worst moments with FENs. It does not mention destructive actions or auth needs, which are safe to assume absent.

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 paragraph, front-loaded with purpose, then details, then usage. It is informative but not overly verbose. Could be slightly more structured with bullet points.

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 complexity of full game analysis, the description covers the main outputs comprehensively. No output schema exists, so the description must detail return values, which it does. It does not mention error handling or PGN format requirements.

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 coverage is 0%, so description must compensate. It explains pgn (required) and user_color (to focus reporting). However, depth and max_plies are not described beyond default values. Partial compensation.

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 analyzes a full game from PGN, providing per-move classification with Korean labels, win% changes, centipawn loss, engine moves, tactical motifs, and a summary with accuracy/ACPL and per-phase breakdown. This differentiates it from siblings like analyze_position (likely single position) and diagnose_weaknesses (post-analysis).

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 explains that setting user_color focuses reporting on one player. It implies the tool is for analyzing a full game, but does not explicitly state when not to use or list alternatives. However, the sibling context provides differentiation.

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

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

No annotations provided, so the description carries the full burden. It discloses expected outputs: centipawns, win%, SAN lines, material, tactical flags. It does not mention side effects or constraints, but the description is transparent about what the tool does and returns.

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 three sentences, front-loaded with action and returns, with no wasted words. It is efficiently structured and easy to scan.

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 no output schema and no annotations, the description covers the main outputs and use case. It lacks some details like limits or prerequisites, but is fairly complete for a straightforward analysis tool.

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%, and the description does not explain individual parameters like depth or multipv. It mentions 'FEN' implicitly but lacks details on parameter meaning or defaults.

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 it evaluates a single position (FEN) and returns engine lines, evaluation, material balance, and tactical flags, distinguishing it from sister tools like analyze_game which likely analyzes entire games.

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 explicitly says 'Use this to explain *why* a move is best in a specific position,' providing clear context for when to use. It does not contrast with siblings, but the guidance is sufficient.

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

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

With no annotations, the description carries the full burden. It discloses that the tool runs engine analysis over many games, is computationally heavy, and suggests limiting max_games. It lists output components. It does not mention auth needs or rate limits, but the behavioral impact (heavy) is clearly conveyed.

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 very concise at three sentences. It front-loads the purpose, then details the rich output, and ends with usage guidance. Every sentence adds value with no waste.

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 no output schema, the description covers return values (accuracy, per-phase breakdown, tactical blind spots with FENs, etc.) adequately. It doesn't specify format or error conditions, but for a coach tool, the level of detail is sufficient for an agent to understand what to expect.

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 only addresses max_games ('keep max_games modest') but does not explain username, source, depth, or speed. Users are left to infer these from the tool name and common sense, which is insufficient for correct 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 tool diagnoses recurring weaknesses from recent games, with specific outputs (accuracy, per-phase, blind spots, etc.). It distinguishes itself from siblings like analyze_game (single game) and fetch_recent_games (just fetch) by emphasizing the aggregation over multiple games.

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 provides guidance on when to use ('core coach tool') and a practical constraint ('keep max_games modest for fast turnaround'). It implies this is heavier than other tools, so alternatives like analyze_game are better for single-game analysis, though not explicitly stated.

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

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

With no annotations provided, the description covers basic behavior (read-only status check) but does not add details like non-destructive nature or specific conditions.

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 two sentences with only 20 words, front-loading the purpose and adding a usage hint without any redundancy.

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, parameterless status-check tool with no output schema, the description thoroughly covers purpose and usage context.

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 zero parameters and 100% schema coverage, so no param info is needed. The description is adequate given the absence of 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?

The description clearly states the tool reports the availability and version of the local Stockfish engine, distinguishing itself from sibling tools that analyze games or positions.

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 second sentence explicitly advises to call this tool first if other tools fail with an engine error, providing clear when-to-use context, though no exclusions are mentioned.

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

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

Without annotations, the description adds value by stating 'No analysis is run here' and mentions public data, but fails to disclose any side effects, rate limits, or read-only guarantee. It partially compensates for missing 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 concise with three sentences, front-loading the purpose and efficiently covering essential details without extraneous text.

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?

The tool has 4 parameters and no output schema. The description lists return fields but lacks structure (array vs object) and omits explanation for 'username' and 'max_games'. It meets minimum completeness but has gaps.

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 coverage is 0%, so description must explain parameters. It explains 'source' and 'speed' with acceptable detail, but 'max_games' and 'username' are not described, leaving gaps. The description provides some added meaning over the schema.

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 verb 'Fetch', the resource 'player's recent games', and the sources 'Lichess or Chess.com', distinguishing it from sibling tools like 'analyze_game' which perform analysis.

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 for fetching game data but does not explicitly state when to use this tool versus alternatives (e.g., for raw data vs analysis). It also lacks prerequisites or exclusions.

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

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

Without annotations, the description carries the full burden. It discloses that it runs diagnose_weaknesses internally, returns drill positions with specific details (FEN, side, engine move), and orders by weaknesses. It doesn't mention read-only nature or potential side effects, but the behavior is mostly transparent.

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 two sentences long, very concise with no fluff. The first sentence captures the core purpose, and the second details the behavior. It is well-structured and efficient.

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 6 parameters, no output schema, and no annotations, the description lacks essential context. It does not explain parameter meanings, error conditions, prerequisites, or the output format beyond a brief mention. This leaves an agent underinformed for proper invocation.

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%, and the description provides no explanations for any of the 6 parameters. The titles and defaults are insufficient for an agent to understand the meaning and constraints of parameters like source, max_games, depth, or num_drills.

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 it builds a personalised drill set from the player's own mistakes, distinguishing it from sibling tools like diagnose_weaknesses which only analyze weaknesses. It specifies the source (blunders) and output format (FEN, side to move, engine move).

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 when to use (to generate drills from mistakes) but does not explicitly state when not to use or provide alternative tool comparisons. The mention of 'optional Lichess daily puzzle' gives some context, but lacks explicit usage guidelines.

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