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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states 'Create a new persistent memory node', implying a write operation, but doesn't address permissions, idempotency, rate limits, or what 'persistent' entails (e.g., storage duration, retrieval guarantees). This leaves significant gaps for a mutation tool.

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, efficient sentence that front-loads the core purpose ('Create a new persistent memory node') and adds a useful detail ('with optional associations'). Every word earns its place, with no redundancy or fluff.

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 (which handles return values) and 100% schema coverage for parameters, the description is minimally adequate. However, as a mutation tool with no annotations, it should provide more behavioral context (e.g., side effects, error conditions) to be fully complete for an AI agent.

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 100%, with clear descriptions for both parameters in the schema. The description adds minimal value by mentioning 'optional associations', which is already implied by the schema's optional 'associations' field. No additional semantic context is provided beyond what the schema documents.

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 action ('Create') and resource ('persistent memory node'), distinguishing it from sibling tools like 'addShortTermMemory' and 'addThought' by specifying 'persistent' and 'memory node'. However, it doesn't explicitly differentiate from 'saveMemory' or 'updateLongTermMemory', which prevents a perfect score.

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 no guidance on when to use this tool versus alternatives like 'addShortTermMemory', 'saveMemory', or 'updateLongTermMemory'. It mentions 'optional associations' but doesn't explain when associations are appropriate or when other tools might be better suited.

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 carries the full burden. It discloses key behavioral traits: 'temporary', 'FIFO', and 'limited capacity', which help understand how the tool behaves beyond just adding memory. However, it lacks details on permissions, rate limits, or error 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 a single, efficient sentence that front-loads the core action and includes essential behavioral details ('FIFO, limited capacity') without any wasted words. Every element earns its place.

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 (which handles return values), no annotations, and a simple single-parameter input with full schema coverage, the description is reasonably complete. It covers the core behavior but could improve by addressing usage relative to siblings.

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 100%, so the input schema fully documents the 'text' parameter. The description adds no additional meaning about parameters beyond what the schema provides, meeting the baseline for high coverage.

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 action ('Add') and resource ('temporary memory to the short-term cache'), making the purpose understandable. However, it doesn't explicitly differentiate from siblings like 'addLongTermMemory' or 'saveMemory' beyond mentioning 'short-term' vs 'cache'.

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 no guidance on when to use this tool versus alternatives like 'addLongTermMemory' or 'saveMemory'. It mentions 'FIFO, limited capacity' which hints at constraints but doesn't specify use cases 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?

No annotations are provided, so the description carries full burden. It mentions 'Add a thought' which implies a write/mutation operation, but doesn't disclose behavioral traits like permissions needed, whether it's idempotent, rate limits, or what happens on failure. This leaves significant gaps for an agent to understand how to use it safely and effectively.

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, clear sentence with no wasted words. It's front-loaded and efficiently conveys the core purpose without unnecessary elaboration, making it easy for an agent to parse quickly.

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 (which covers return values), 5 parameters with full schema coverage, and no annotations, the description is minimally adequate. However, as a mutation tool with no behavioral disclosure, it should do more to explain usage context and potential side effects to be fully complete for an agent.

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 100%, so the schema already documents all parameters thoroughly. The description adds no additional meaning beyond the schema, such as explaining relationships between parameters (e.g., how 'parentThoughtId' relates to 'chainId'). Baseline 3 is appropriate as the schema does the heavy lifting.

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 action ('Add') and resource ('thought to an existing thought chain'), making the purpose understandable. However, it doesn't differentiate from sibling tools like 'branchThought' or 'evaluateThought', which also manipulate thoughts in some way, so it misses full sibling distinction.

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 no guidance on when to use this tool versus alternatives. With siblings like 'branchThought' (for branching) and 'evaluateThought' (for evaluation), there's no indication of when 'addThought' is appropriate, such as for appending to a linear chain versus other operations.

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 are provided, so the description carries the full burden of behavioral disclosure. It states the action ('Create a branch') but doesn't explain what this entails—e.g., whether it modifies the original thought, creates a new thought in memory, requires specific permissions, or has side effects like updating chains. For a mutation tool with zero annotation coverage, this is a significant gap in transparency.

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, efficient sentence that front-loads the core action and purpose without unnecessary words. Every part ('Create a branch from an existing thought to explore alternative paths') contributes directly to understanding the tool, making it appropriately sized and well-structured.

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 (which handles return values), no annotations, and moderate complexity with 4 parameters, the description is minimally complete. It covers the basic purpose but lacks behavioral details (e.g., mutation effects) and parameter guidance, leaving gaps that could hinder effective use by an AI agent without further 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?

Schema description coverage is 50%, with parameters 'thoughtId' and 'newThought' documented in the schema but 'type' and 'confidence' lacking descriptions. The description adds no parameter-specific information beyond what's implied by the tool name (e.g., 'thoughtId' for branching). It doesn't compensate for the coverage gap by explaining enum values for 'type' or the meaning of 'confidence', resulting in baseline adequacy.

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 ('Create a branch') and resource ('from an existing thought') with a specific purpose ('to explore alternative paths'). It distinguishes this from sibling tools like 'addThought' or 'completeThoughtProcess' by focusing on branching rather than adding or finishing thoughts. However, it doesn't explicitly differentiate from all siblings like 'evaluateThought' or 'updateLongTermMemory' in the same sentence.

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 no explicit guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an existing thought), exclusions (e.g., when not to branch), or comparisons to sibling tools like 'addThought' for new thoughts or 'evaluateThought' for assessing existing ones. The purpose implies usage for exploration but lacks actionable context.

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 are provided, so the description carries the full burden of behavioral disclosure. While 'Clear all short-term memories' implies a destructive operation, it doesn't specify whether this is reversible, what happens to associated data, or any side effects. For a tool with no annotation coverage, this is insufficient.

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, efficient sentence with zero waste—'Clear all short-term memories'—directly conveying the tool's purpose without unnecessary elaboration. It's appropriately sized and front-loaded.

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 no parameters and an output schema exists, the description is minimally adequate. However, as a potentially destructive operation with no annotations, it should provide more context on behavior (e.g., confirmation, effects) to be fully complete, leaving room for improvement.

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 tool has 0 parameters with 100% schema description coverage, so the schema fully documents the absence of inputs. The description doesn't need to add parameter details, and it correctly implies no parameters are required, earning a baseline score above 3 for this scenario.

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 action ('Clear') and the target resource ('all short-term memories'), providing a specific verb+resource combination. However, it doesn't explicitly differentiate from sibling tools like 'deleteLongTermMemory' or 'saveMemory', which prevents a perfect score.

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 no guidance on when to use this tool versus alternatives. With many sibling tools related to memory management (e.g., 'deleteLongTermMemory', 'saveMemory'), there's no indication of context, prerequisites, or exclusions for using 'clearShortTermMemory'.

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 carries full burden but lacks behavioral details. It implies a mutation ('Mark as complete and store'), but doesn't disclose permissions needed, whether this is irreversible, what happens to the thought process after completion (e.g., archived or deleted), or any rate limits. The description adds minimal context beyond the basic action.

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, efficient sentence with zero waste—it directly states the tool's function without unnecessary words. It's appropriately sized and front-loaded, making it easy to parse quickly.

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 moderate complexity (a mutation with 2 required parameters), no annotations, but a 100% schema coverage and an output schema, the description is minimally adequate. It states the core action but lacks details on behavioral implications, usage context, and output expectations, leaving gaps that could hinder effective agent use.

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 100%, with clear parameter descriptions in the schema, so the baseline is 3. The description doesn't add meaning beyond the schema—it mentions 'conclusion' but doesn't elaborate on format, length, or content expectations, nor does it explain 'chainId' beyond what the schema 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 the action ('Mark as complete and store') and the resource ('thought process'), making the purpose understandable. However, it doesn't differentiate from sibling tools like 'pauseThinking' or 'resumeThinking' that also manage thought process states, nor does it specify what 'complete' means operationally compared to other terminal states.

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. It doesn't mention prerequisites (e.g., must have an active thought process), exclusions (e.g., cannot complete a paused process), or related tools like 'startThoughtProcess' for initiation or 'getActiveChains' for checking status, leaving usage context unclear.

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 carries the full burden of behavioral disclosure. It mentions that deletion removes the node from 'all associations', which adds some context beyond a simple delete operation, but it lacks details on permissions, reversibility, side effects, or response format. For a destructive tool, this is insufficient.

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, efficient sentence that directly states the tool's function without unnecessary words. It's front-loaded and wastes no space, earning a top score for conciseness.

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 complexity (destructive operation), lack of annotations, and presence of an output schema, the description is minimally adequate. It covers the basic action but misses critical details like safety warnings or behavioral traits. The output schema might handle return values, but the description doesn't compensate for the annotation gap.

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 100% description coverage, with the 'id' parameter clearly documented. The description doesn't add any extra meaning about the parameter beyond what the schema provides, such as format or constraints, so it meets the baseline for high schema coverage.

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 action ('Delete') and resource ('a memory node'), making the purpose evident. However, it doesn't explicitly differentiate from sibling tools like 'clearShortTermMemory' or 'updateLongTermMemory', which might also involve memory removal or modification, so it's not a perfect 5.

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 no guidance on when to use this tool versus alternatives like 'clearShortTermMemory' or 'updateLongTermMemory', nor does it mention prerequisites or exclusions. It's a basic statement of function without contextual usage advice.

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 are provided, so the description carries the full burden of behavioral disclosure. It mentions 'evaluate and update', implying a mutation operation, but doesn't specify permissions required, side effects (e.g., if this affects other thoughts or memory), error conditions, or response format. This leaves significant gaps in understanding the tool's behavior beyond basic input-output.

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, efficient sentence that directly states the tool's purpose without unnecessary words. It's front-loaded with the core action, making it easy to parse quickly.

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 (not provided in details but indicated as present), the description doesn't need to explain return values. However, as a mutation tool with no annotations and moderate complexity (3 required parameters), the description is minimal—it covers the basic purpose but lacks behavioral context and usage guidelines, making it incomplete for safe and effective use.

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 100% description coverage, with clear documentation for 'thoughtId', 'confidence', and 'reasoning'. The description adds no additional parameter semantics beyond what's in the schema, such as format examples or contextual usage of parameters. Baseline 3 is appropriate as the schema does the heavy lifting.

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 'Evaluate and update the confidence level of a thought' clearly states the action (evaluate and update) and resource (confidence level of a thought), but it's somewhat vague about what 'evaluate' entails beyond updating confidence. It doesn't distinguish this tool from siblings like 'updateLongTermMemory' or 'completeThoughtProcess' which might also involve confidence adjustments in a thought system.

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 no guidance on when to use this tool versus alternatives. With siblings like 'updateLongTermMemory', 'completeThoughtProcess', and 'branchThought' that might handle thought modifications, there's no indication of specific contexts, prerequisites, or exclusions for this tool's use.

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 are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves active thought chains but doesn't explain what 'active' means, how results are formatted, if there are rate limits, or any side effects. This is a significant gap for a tool with no annotation coverage.

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, efficient sentence that directly states the tool's purpose without any fluff or redundancy. It's front-loaded and wastes no words, making it easy for an agent to parse quickly.

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 0 parameters, 100% schema coverage, and an output schema exists, the description is minimally adequate. However, it lacks behavioral context (e.g., what 'active' entails, response format hints) that would help an agent use it correctly, especially with no annotations to fill 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?

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description doesn't add parameter details, which is appropriate here, but it could have mentioned if any implicit parameters (like filters) are applied, though not required for a high score.

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 action ('Get') and the resource ('all currently active thought chains'), which is specific and unambiguous. However, it doesn't explicitly differentiate from sibling tools like 'getCurrentThoughtChain' or 'getThinkingProgress', which might have overlapping or related purposes.

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 no guidance on when to use this tool versus alternatives. With siblings like 'getCurrentThoughtChain' and 'getThinkingProgress', there's no indication of context, prerequisites, or exclusions, leaving the agent to guess based on tool names alone.

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 carries full burden for behavioral disclosure. While 'Get' implies a read operation, it doesn't specify whether this requires authentication, has rate limits, returns paginated results, or what happens with invalid IDs. For a tool with zero annotation coverage, this leaves significant behavioral questions unanswered.

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 perfectly concise at just 8 words, front-loading the essential information with zero wasted language. Every word earns its place by specifying what is retrieved ('direct association IDs') from what resource ('a memory node').

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 (which handles return values) and 100% schema coverage for its single parameter, the description is minimally adequate. However, with no annotations and multiple sibling retrieval tools, it should provide more context about its specific role in the memory system to help agents choose correctly among alternatives.

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 has 100% description coverage, with the single parameter 'id' clearly documented as 'The memory node ID.' The description adds no additional parameter semantics beyond what the schema already provides, so the baseline score of 3 is appropriate given the schema does the heavy lifting.

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 action ('Get') and resource ('direct association IDs of a memory node'), making the purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'getActiveChains' or 'getCurrentThoughtChain' that might also retrieve related memory structures, leaving room for potential confusion about when to choose this specific tool.

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 no guidance on when to use this tool versus alternatives. With siblings like 'getActiveChains' and 'getCurrentThoughtChain' that might retrieve related memory data, there's no indication of what distinguishes this tool's scope or when it's the appropriate choice over other retrieval tools in the system.

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 carries the full burden of behavioral disclosure. It states the action is 'retrieve', implying a read-only operation, but doesn't mention any behavioral traits like permissions, rate limits, or what 'current state' entails (e.g., real-time vs. cached). This leaves significant gaps for a tool that interacts with thought chains.

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, efficient sentence that directly states the tool's purpose without unnecessary words. It is appropriately sized and front-loaded, making it easy for an agent to parse quickly.

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 moderate complexity (retrieving thought chain states) and the presence of an output schema (which handles return values), the description is minimally adequate. However, it lacks context on behavioral aspects and usage guidelines, making it incomplete for optimal agent understanding without additional structured data.

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 100% description coverage, with 'chainId' clearly documented. The description adds no additional meaning beyond what the schema provides, such as format examples or context for the ID. This meets the baseline score when schema coverage is high.

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 'retrieve' and the resource 'current state of a thought chain with all thoughts', making the purpose specific and understandable. However, it doesn't explicitly differentiate from sibling tools like 'getActiveChains' or 'getThinkingProgress', which prevents a perfect score.

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 no guidance on when to use this tool versus alternatives like 'getActiveChains' or 'getThinkingProgress'. It lacks context about prerequisites, such as needing an active thought chain, or exclusions, which leaves the agent without usage direction.

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 are provided, so the description carries the full burden of behavioral disclosure. It mentions retrieving associations up to a depth, which hints at read-only behavior, but doesn't clarify permissions, rate limits, error handling, or what 'associations' entail. For a tool with no annotations, this leaves significant gaps in understanding its operational traits.

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, efficient sentence that front-loads the core action ('retrieve a memory node by ID') and includes key details ('with its associations up to specified depth'). There's no wasted wording, making it highly concise and well-structured for quick understanding.

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 moderate complexity (2 parameters, read-focused), 100% schema coverage, and the presence of an output schema (which handles return values), the description is reasonably complete. It covers the main action and scope but could improve by addressing behavioral aspects like error cases or sibling tool differentiation, which would enhance completeness further.

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 100%, so the schema already documents both parameters ('id' and 'depth') with descriptions. The description adds minimal value by mentioning 'associations up to specified depth', which aligns with the schema but doesn't provide additional syntax or format details. Baseline 3 is appropriate as the schema handles most of the parameter documentation.

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 'retrieve' and the resource 'memory node by ID with its associations', which is specific. However, it doesn't explicitly distinguish this tool from sibling tools like 'getAssociations' or 'searchLongTermMemory', which might have overlapping functionality. The purpose is clear but lacks sibling differentiation.

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 no guidance on when to use this tool versus alternatives. With siblings like 'getAssociations' and 'searchLongTermMemory' available, there's no indication of context, prerequisites, or exclusions. It implies usage by specifying parameters but offers no explicit when/when-not instructions.

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 are provided, so the description carries full burden. It states this is a 'Get' operation which implies read-only behavior, but doesn't disclose any behavioral traits like whether it requires specific permissions, what format the statistics are returned in, or if there are any rate limits or performance considerations.

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, efficient sentence that states exactly what the tool does without any unnecessary words. It's appropriately sized for a zero-parameter tool and front-loads the essential information.

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 zero-parameter tool with an output schema, the description is minimally complete. It identifies the tool's purpose but doesn't provide context about what specific memory statistics are returned or how this differs from similar statistical tools. The output schema will handle return value documentation, but the description could better situate this tool within the broader memory/cognitive system 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 tool has 0 parameters with 100% schema description coverage, so the baseline is 4. The description doesn't need to compensate for any parameter documentation gaps since there are no parameters to document.

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 'Get' and the resource 'statistics about the memory system', which is specific and unambiguous. However, it doesn't explicitly differentiate from sibling tools like getThinkingStats or getThinkingProgress, which also retrieve statistical data about cognitive processes.

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 no guidance on when to use this tool versus alternatives. With siblings like getThinkingStats and getThinkingProgress that also retrieve statistics, there's no indication of what distinguishes this tool's focus on 'memory system' statistics from other statistical tools in the context.

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 are provided, so the description carries full burden. It doesn't disclose behavioral traits such as whether this is a read-only operation, if it requires specific permissions, potential rate limits, or what happens on errors. The description only states what it does, not how it behaves, leaving critical gaps for an AI agent.

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, efficient sentence with zero waste. It's front-loaded with the core purpose and appropriately sized for a simple tool with one parameter. Every word earns its place, making it easy to parse quickly.

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 (one parameter) and the presence of an output schema (which handles return values), the description is minimally complete. However, it lacks behavioral context and usage guidelines, which are important even for simple tools. It meets basic needs but leaves the agent to guess about proper application.

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 100%, so the schema fully documents the single parameter 'taskType'. The description adds no additional meaning beyond what the schema provides—it doesn't explain what constitutes a valid 'task type' or provide examples. Baseline 3 is appropriate as the schema handles parameter documentation adequately.

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 ('Get') and resource ('recommended cognitive mode') with a specific purpose ('for a specific task type'). It distinguishes from siblings like 'switchCognitiveMode' (which changes mode) and 'getThinkingStats' (which provides statistics), though it doesn't explicitly mention these distinctions. The purpose is specific but could be more differentiated from related 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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, when-not-to-use scenarios, or compare with siblings like 'getThinkingStats' or 'switchCognitiveMode'. The agent must infer usage from context alone, which is insufficient for optimal tool selection.

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 carries the full burden of behavioral disclosure. It states the retrieval action and ordering but doesn't cover critical aspects like whether this is a read-only operation, potential side effects, authentication needs, rate limits, or error conditions. For a tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.

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, efficient sentence that front-loads the core purpose ('Retrieve all short-term memories') and adds a useful constraint ('newest first') without any wasted words. It's appropriately sized for a simple retrieval tool.

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 (0 parameters, no annotations, but with an output schema), the description is minimally adequate. It explains what the tool does but lacks context on usage, behavioral details, or integration with sibling tools. The presence of an output schema means return values are documented elsewhere, but the description doesn't fully compensate for the missing behavioral transparency.

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 tool has 0 parameters, and the input schema has 100% description coverage (though empty). The description adds no parameter-specific information, which is appropriate here. A baseline of 4 is applied for zero-parameter tools, as there's no need to compensate for schema gaps.

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 action ('Retrieve') and resource ('all short-term memories') with a specific ordering constraint ('newest first'), which distinguishes it from other memory-related tools like getLongTermMemory or searchLongTermMemory. However, it doesn't explicitly differentiate from getMemoryStats or getThinkingStats which might also involve memory retrieval, keeping it from a perfect score.

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 no guidance on when to use this tool versus alternatives like getLongTermMemory, searchLongTermMemory, or getMemoryStats. It lacks context about prerequisites, such as whether short-term memories must exist or if this is part of a thought process, and doesn't mention exclusions or complementary tools.

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 carries the full burden of behavioral disclosure. It states this is a 'Get' operation, implying read-only behavior, but doesn't clarify if it requires specific permissions, returns real-time or cached data, or has rate limits. For a tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.

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, efficient sentence that directly states the tool's purpose without unnecessary words. It is front-loaded with the core functionality, making it easy for an agent to parse quickly. Every word earns its place.

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 (which handles return values), one parameter with full schema coverage, and no annotations, the description is reasonably complete for a simple read operation. It specifies the resource ('thought chain') and action ('Get progress statistics'), though it could better explain what 'progress' entails to fully compensate for the lack of annotations.

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 description coverage is 100%, with the single parameter 'chainId' fully documented in the schema. The description adds no additional meaning about the parameter beyond what the schema provides (e.g., format examples or context). With high schema coverage, the baseline score 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 verb ('Get') and resource ('progress statistics for a thought chain'), making the purpose understandable. It distinguishes this from tools like 'getThinkingStats' or 'getActiveChains' by focusing specifically on progress within a chain. However, it doesn't specify what 'progress statistics' include, leaving some ambiguity.

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 no guidance on when to use this tool versus alternatives like 'getThinkingStats' or 'getActiveChains'. It doesn't mention prerequisites (e.g., needing an active thought chain) or exclusions. The agent must infer usage from the tool name and context alone.

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 are provided, so the description carries full burden for behavioral disclosure. It states this is a 'get' operation, implying read-only behavior, but doesn't specify any constraints like authentication needs, rate limits, or what 'overall' entails (e.g., aggregated data, real-time vs. historical). This leaves significant gaps in understanding how the tool behaves.

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, clear sentence with no wasted words. It's front-loaded with the core purpose and appropriately concise for a simple tool with no parameters.

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 0 parameters, 100% schema coverage, and an output schema exists, the description is minimally adequate. However, it lacks context about what 'overall thinking process statistics' includes (e.g., metrics like thought count, duration, efficiency), which could help the agent interpret results without relying solely on the output schema.

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 tool has 0 parameters, and schema description coverage is 100%, so no parameter documentation is needed. The description appropriately doesn't discuss parameters, which is efficient. A baseline of 4 is applied since no parameters exist, and the description doesn't add unnecessary details.

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 'Get overall thinking process statistics' clearly states the action (get) and resource (thinking process statistics), which is adequate. However, it doesn't differentiate from similar sibling tools like getMemoryStats or getThinkingProgress, leaving ambiguity about what specific statistics this tool provides versus those alternatives.

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 no guidance on when to use this tool versus alternatives. With multiple sibling tools like getMemoryStats and getThinkingProgress that also retrieve statistical or progress data, the agent has no indication of which tool is appropriate for different scenarios, such as overall process metrics versus memory-specific stats.

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 carries full burden for behavioral disclosure. It states the action ('pause') but doesn't explain what pausing entails—whether it's reversible, if it preserves state, or what happens to the thought chain. It also omits critical details like permissions needed, side effects, or error conditions. For a mutation tool with zero annotation coverage, this leaves significant behavioral gaps.

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, efficient sentence with zero wasted words. It's front-loaded with the core action ('pause') and resource ('active thought process'), making it immediately scannable. Every word earns its place, and there's no redundancy or fluff.

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 (which handles return values) and 100% schema coverage for parameters, the description's minimalism is partially excusable. However, as a mutation tool with no annotations, it should still clarify behavioral aspects like reversibility or side effects. The description is adequate but leaves gaps in usage context and behavioral transparency.

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 100%, with both parameters (chainId, reason) clearly documented in the schema. The description adds no additional parameter semantics beyond implying the tool operates on a thought process (linked to chainId). Since the schema does the heavy lifting, the baseline score of 3 is appropriate—the description doesn't enhance or contradict parameter understanding.

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 'Pause an active thought process' clearly states the verb ('pause') and resource ('active thought process'), making the purpose immediately understandable. It distinguishes from siblings like 'resumeThinking' and 'completeThoughtProcess' by specifying the pause action rather than continuation or termination. However, it doesn't explicitly mention the chainId parameter's role in identifying which process to pause.

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 no guidance on when to use this tool versus alternatives like 'resumeThinking' or 'completeThoughtProcess'. There's no mention of prerequisites (e.g., only works on active chains), nor does it specify what constitutes an 'active thought process' that can be paused. The agent must infer usage from the tool name alone.

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 carries full burden for behavioral disclosure. While 'Resume' implies continuation of an existing process, it doesn't specify what happens during resumption (does thinking continue automatically?), whether there are side effects, or what the output contains. For a tool with no annotation coverage, this leaves significant behavioral questions unanswered.

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, efficient sentence that communicates the core purpose without any wasted words. It's appropriately sized for a simple tool with one parameter and is front-loaded with the essential information.

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 relative simplicity (1 parameter, 100% schema coverage, output schema exists), the description is adequate but minimal. The existence of an output schema means the description doesn't need to explain return values. However, for a tool that presumably resumes a cognitive process, more context about what 'resuming' entails would be helpful given the lack of annotations.

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 100% with the single parameter 'chainId' well-documented in the schema. The description doesn't add any parameter-specific information beyond what the schema provides. According to guidelines, when schema coverage is high (>80%), the baseline is 3 even with no param info in description.

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 ('Resume') and resource ('a paused thought process'), making the purpose immediately understandable. It distinguishes from siblings like 'pauseThinking' (the inverse operation) and 'startThoughtProcess' (initial creation). However, it doesn't explicitly mention the 'chainId' parameter which is central to the operation, keeping it from a perfect score.

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 context by specifying 'paused thought process' - suggesting this should only be used after 'pauseThinking'. However, it doesn't explicitly state when NOT to use it (e.g., on active or completed chains) or mention alternatives like 'startThoughtProcess' for new chains. The guidance is present but incomplete.

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 carries full burden for behavioral disclosure. It states the action is a manual trigger for saving, implying a write operation, but lacks details on permissions, side effects, or response format. This is inadequate for a mutation tool with zero annotation coverage.

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, efficient sentence that directly states the tool's purpose without any wasted words. It is appropriately sized and front-loaded, making it easy to parse.

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 0 parameters, 100% schema coverage, and an output schema exists, the description is minimally complete. However, as a mutation tool with no annotations, it should ideally include more behavioral context, such as confirmation of success or error handling.

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 tool has 0 parameters, and schema description coverage is 100%, so no parameter information is needed. The description appropriately doesn't discuss parameters, earning a baseline score of 4 for not adding unnecessary details.

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 action ('manually trigger saving') and resource ('all long-term memories to disk'), making the purpose specific and understandable. However, it doesn't explicitly differentiate from sibling tools like 'addLongTermMemory' or 'updateLongTermMemory', which prevents a perfect score.

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 no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, timing considerations, or related tools, leaving the agent without context for appropriate invocation.

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 are provided, so the description carries full burden. It mentions 'text matching' but doesn't disclose behavioral traits like whether this is a read-only operation, how results are returned (e.g., pagination, format), performance considerations, or error handling. For a search tool with zero annotation coverage, this is a significant gap.

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, efficient sentence with zero waste. It's front-loaded with the core purpose and avoids unnecessary elaboration, making it easy to parse quickly.

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 moderate complexity (search operation with 3 parameters), no annotations, but a rich input schema (100% coverage) and an output schema (present), the description is minimally adequate. The output schema likely handles return values, but the description lacks context on usage scenarios, behavioral traits, or integration with sibling tools, leaving gaps for an AI agent.

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 100%, so the schema already documents all parameters (keyword, limit, caseSensitive) with their types and defaults. The description adds no additional meaning beyond what the schema provides, such as search algorithm details or examples. Baseline 3 is appropriate when the schema does the heavy lifting.

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 action ('search') and target resource ('memory nodes') with the mechanism ('by keyword (text matching)'). It distinguishes from siblings like 'getLongTermMemory' or 'getAssociations' by specifying search functionality, though it doesn't explicitly contrast with all alternatives.

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 like 'getLongTermMemory' (which might retrieve specific memories) or 'getAssociations' (which might find related concepts). The description implies usage for keyword-based searching but offers no context about prerequisites, exclusions, or comparative scenarios.

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 carries full burden but lacks behavioral details. It states it 'starts' something but doesn't clarify if this is a read/write operation, what happens to existing processes, whether it requires specific permissions, or what the output entails (though an output schema exists). This is inadequate for a tool that likely initiates a mutable state.

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, efficient sentence that front-loads the core action ('Start a new thought process chain') and purpose ('with a goal'). There is no wasted wording, making it highly concise and well-structured.

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 complexity (initiating a process in a cognitive system), the description is minimal. However, with 100% schema coverage and an output schema, it avoids explaining parameters or return values. Still, for a tool with no annotations and many siblings, it should provide more context on behavior and usage to be fully complete.

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 100%, so the schema fully documents the 'goal' and 'context' parameters. The description mentions 'with a goal', aligning with the required parameter, but adds no extra meaning beyond what the schema provides (e.g., examples of valid goals or context usage). Baseline 3 is appropriate here.

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 action ('Start') and resource ('new thought process chain') with a specific purpose ('with a goal'), distinguishing it from sibling tools like 'getActiveChains' or 'completeThoughtProcess'. However, it doesn't explicitly differentiate from similar initiation tools (e.g., 'branchThought' might also start a chain), so it's not a perfect 5.

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 no guidance on when to use this tool versus alternatives like 'branchThought' (which might start a branched chain) or 'getActiveChains' (which retrieves existing ones). It mentions a 'goal' parameter but doesn't explain prerequisites or contextual triggers for starting a new process.

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 are provided, so the description carries the full burden of behavioral disclosure. It mentions switching modes but doesn't describe what happens after switching (e.g., does it affect ongoing thought chains, require permissions, have side effects, or include confirmation). For a tool that likely alters thinking behavior, this lack of detail is a significant gap.

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, efficient sentence that directly states the tool's function. It's front-loaded with the core action ('Switch the cognitive mode'), though it could be more specific. There's no wasted text, but it might be too brief for a tool with potential behavioral implications.

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 moderate complexity (affecting thinking processes), no annotations, and an output schema (which handles return values), the description is minimally adequate. It covers the basic purpose but lacks details on behavior, usage context, and parameter nuances, leaving gaps for an AI agent to infer correct 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 100%, with the schema providing clear descriptions for both parameters ('mode' with enum values and 'chainId' as optional). The description adds no additional meaning beyond the schema, such as explaining what each mode entails or how chainId applies the mode. Baseline is 3 since the schema does the heavy lifting.

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 states the tool's purpose as 'Switch the cognitive mode for thinking processes', which includes a verb ('Switch') and resource ('cognitive mode'), but it's vague about what 'thinking processes' refers to and doesn't distinguish it from sibling tools like 'getOptimalModeForTask' or 'evaluateThought'. It doesn't specify whether this affects current thinking, future thinking, or specific chains.

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. It doesn't mention when to switch modes (e.g., during stuck thinking, for different tasks), when not to use it, or how it relates to siblings like 'getOptimalModeForTask' (which might suggest modes) or 'startThoughtProcess' (which might involve mode selection). Usage is implied but 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, the description carries full burden but lacks critical behavioral details. It states the tool updates memory, implying mutation, but doesn't disclose permissions needed, whether updates are reversible, rate limits, or how partial updates (e.g., only text) affect existing data. This is inadequate for a mutation tool with zero annotation coverage.

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, efficient sentence with zero waste. It front-loads the core action and directly lists the updatable components, making it easy to parse quickly.

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 (which handles return values) and 100% parameter coverage, the description's gaps in behavioral transparency and usage guidelines are partially mitigated. However, as a mutation tool with no annotations, it should provide more context on safety and prerequisites to be fully complete.

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 100%, so the schema fully documents parameters (id, newText, newAssociations). The description adds no additional meaning beyond implying these are the updatable fields. Baseline 3 is appropriate when the schema does the heavy lifting.

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 action ('Update') and target ('a memory node's text and/or associations'), which distinguishes it from siblings like 'addLongTermMemory' or 'deleteLongTermMemory'. However, it doesn't explicitly differentiate from 'saveMemory' or specify what constitutes a 'memory node' beyond the ID parameter.

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 no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an existing memory node), contrast with 'addLongTermMemory' for new nodes, or explain when to update text versus associations. Usage is implied but not articulated.

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