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 'Store a new memory' implies a write operation, the description doesn't address important behavioral aspects like whether this requires authentication, what happens on success/failure, whether there are rate limits, or how the memory is persisted. The examples help but don't cover operational 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 perfectly concise with two sentences that each earn their place. The first sentence states the core purpose, and the second provides usage guidance with helpful examples. No wasted words, and it's 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?

For a write operation with no annotations and no output schema, the description provides adequate basic context about purpose and usage. However, it lacks important contextual information about what happens after storing (e.g., confirmation, memory ID returned), error conditions, or how this integrates with the broader memory system given the many sibling tools.

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?

With 75% schema description coverage, the schema already documents most parameters well. The description adds no specific parameter information beyond what's in the schema. The baseline of 3 is appropriate since the schema does the heavy lifting, but the description doesn't compensate for the 25% coverage gap (the 'tags' parameter has minimal schema 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 action ('Store a new memory') and resource ('memory'), making the purpose immediately understandable. It distinguishes from siblings like 'update_memory' or 'delete_memory' by specifying 'new' creation. However, it doesn't explicitly differentiate from 'save_session' which might also store memories in a session context.

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 clear guidance on when to use this tool ('when something is worth remembering') with examples of what constitutes a memory (preference, fix, decision, procedure). This helps the agent understand appropriate contexts. However, it doesn't explicitly state when NOT to use it or mention specific alternatives among the many sibling 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?

No annotations are provided, so the description carries the full burden. It discloses the irreversible nature ('permanently delete') and the tool's intent for error correction, which is valuable. However, it lacks details on permissions, error handling, or confirmation steps, leaving behavioral gaps for a destructive operation.

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 front-loaded with the core action ('Permanently delete a memory by ID') and uses two concise sentences to provide usage guidelines. Every sentence adds value without redundancy, making it efficient 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 (destructive operation with no annotations or output schema), the description is reasonably complete. It covers purpose, guidelines, and behavioral traits like permanence. However, it lacks details on response format or error cases, which could be useful 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 the 'id' parameter. The description adds no additional parameter details beyond what the schema provides, but with only one parameter and high coverage, the baseline is 3. The description's context on when to delete compensates slightly, raising it to 4.

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 specific action ('permanently delete') and resource ('a memory by ID'), distinguishing it from siblings like 'deprecate_memory' and 'update_memory'. It explicitly contrasts with 'deprecate_memory' for different use cases, making the purpose unambiguous.

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 explicit guidance on when to use this tool vs. alternatives: 'Prefer deprecate_memory for memories that were once true but are no longer. Only delete memories that were created in error or contain incorrect information.' This clearly defines the appropriate context and excludes other 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?

No annotations are provided, so the description carries the full burden. It discloses key behavioral traits: the memory is excluded from search/recall but retained for history, which clarifies it's a soft delete rather than permanent removal. However, it lacks details on permissions, reversibility, or response format, leaving 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 two sentences, front-loaded with the core action and effect, followed by usage guidance. Every sentence adds value without redundancy, making it efficient and well-structured for quick comprehension.

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 (mutation with 2 parameters), no annotations, and no output schema, the description is mostly complete. It covers purpose, usage, and key behavior, but lacks details on permissions, error handling, or return values, which could be important for full agent understanding.

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 reason). The description adds no additional parameter semantics beyond what the schema provides, such as format examples or constraints. Baseline 3 is appropriate when the schema handles parameter documentation effectively.

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 specific action ('Mark a memory as deprecated') and resource ('memory'), distinguishing it from siblings like delete_memory (removal) or update_memory (modification). It explains the effect ('excluded from search/recall but kept for history'), making the purpose unambiguous and differentiated.

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 states when to use this tool ('Use when a rule or fact is no longer true'), providing clear context. It implies alternatives by contrasting with deletion (kept for history) and other siblings, though it doesn't name specific alternatives like supersede_memory, the guidance is sufficient for informed 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?

No annotations are provided, so the description carries full burden. It discloses key behaviors: returns memories sorted by most recently created, and mentions optional filtering by type. However, it doesn't cover pagination (though 'limit' parameter hints at it), rate limits, authentication needs, or what 'memories' contain structurally. For a read operation with no annotations, this is adequate but leaves 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 highly concise and front-loaded: first sentence states core functionality, second adds sorting detail, third provides usage guidelines. Every sentence earns its place with no wasted words, and it's appropriately sized for a simple listing 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 (2 optional parameters, no output schema, no annotations), the description is reasonably complete. It covers purpose, sorting, filtering, and usage scenarios. However, without annotations or output schema, it could better explain what a 'memory' contains or error conditions, though not strictly required for basic functionality.

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 both parameters (type with enum values, limit with default). The description adds marginal value by mentioning 'optionally filtered by type' and implying sorting, but doesn't provide additional syntax, format, or constraints beyond what's in the schema. Baseline 3 is appropriate when 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 tool's purpose: 'List all memories, optionally filtered by type' specifies the verb (list) and resource (memories) with optional filtering. It distinguishes from siblings like 'search_memory' by emphasizing browsing/auditing vs. targeted search, though not explicitly named. However, it doesn't fully differentiate from 'recall_memory' (which might retrieve specific memories) or 'memory_health' (which could list system status).

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 clear usage context: 'Use to browse what the memory system knows about a topic or to audit stored rules' gives practical scenarios. It implies this is for broad listing vs. alternatives like 'search_memory' for targeted queries, but doesn't explicitly state when NOT to use it or name specific alternatives among the 11 siblings.

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. It describes the core behavior (loading recent session state) and timing (start of conversation), but doesn't disclose important behavioral traits like what happens if no session exists, whether this requires authentication, what data format is returned, or if there are rate limits. The description adds basic context but leaves significant 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 perfectly concise: two sentences that each earn their place. The first states what the tool does, the second states when to use it. No wasted words, well-structured, and front-loaded with the core purpose.

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 annotations, no output schema, and a parameterless tool, the description provides adequate but incomplete context. It explains the purpose and timing well, but doesn't address what constitutes 'session state', what format it returns, error conditions, or how this integrates with sibling tools like 'save_session'. For a state management tool, more behavioral detail would be helpful.

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. The description appropriately doesn't waste space discussing parameters that don't exist. It focuses instead on the tool's purpose and usage context, which is the correct approach for a parameterless tool.

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's purpose: 'Load the most recent session state' specifies the verb (load) and resource (session state). It distinguishes from siblings like 'save_session' by focusing on retrieval rather than storage, but doesn't explicitly differentiate from other read operations like 'list_memories' or 'recall_memory'.

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 explicit usage guidance: 'Call this at the start of a conversation to pick up where the last instance left off.' This tells the agent exactly when to use this tool (initialization/continuation scenarios) and implies it shouldn't be used mid-conversation for other purposes.

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. It states the tool detects contradictions and returns pairs, but lacks details on behavioral traits such as performance characteristics (e.g., computational cost, speed), error handling, or side effects (e.g., whether it modifies memories). This is a significant gap for a tool with potential complexity in memory analysis.

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 purpose ('detect contradictions between active memories') and follows with output specifics. Every word earns its place with no waste, 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 in analyzing memory contradictions, no annotations, and no output schema, the description is minimally adequate. It covers the core purpose and output format but lacks details on behavioral context, error cases, or integration with sibling tools, leaving gaps for 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?

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description appropriately adds value by explaining the tool's function and output without redundant parameter details, aligning with the baseline for zero 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 specific action ('detect contradictions') and resource ('between active memories'), with explicit output detail ('returns pairs of memories that assert and negate the same topic'). It distinguishes from siblings like 'list_memories' or 'search_memory' by focusing on contradiction detection rather than retrieval or modification.

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 explicit guidance on when to use this tool versus alternatives is provided. The description implies usage when checking for contradictions among memories, but it doesn't specify prerequisites (e.g., requires active memories), exclusions, or direct comparisons to siblings like 'memory_health' for broader memory analysis.

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. It discloses what the tool returns (score, conflict count, stale count, status distribution), which is helpful behavioral information. However, it doesn't mention potential side effects, performance characteristics, or error conditions that might be relevant for a health check operation.

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 extremely concise with just two sentences that both earn their place. The first sentence states the purpose and return values, while the second provides usage guidance. There's no wasted language or 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 health check tool with no annotations and no output schema, the description does well by specifying what metrics are returned. However, it could be more complete by explaining what the different return values mean (e.g., what constitutes a 'good' score, what conflicts or stale items indicate) or providing more context about the memory system being checked.

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 single parameter 'stale_days' fully documented in the schema. The description doesn't add any parameter-specific information beyond what's in the schema, 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 specific action ('Run a health check') and resource ('on the memory system'), distinguishing it from sibling tools like list_memories or memory_conflicts. It provides a concrete purpose that is not just a restatement of the tool name.

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 states when to use this tool ('Use to audit memory quality'), providing clear context and distinguishing it from other memory-related tools that perform different operations like adding, deleting, or updating memories.

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 the action ('promote') and the trust level progression, but it lacks details on permissions required, whether the operation is reversible, potential side effects (e.g., on related memories), or error handling. This is a significant gap 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 very concise and front-loaded, consisting of two sentences that directly convey the tool's purpose and usage context without any wasted words. Every sentence earns its place by providing essential information efficiently.

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 a mutation tool (promoting trust levels) with no annotations and no output schema, the description is incomplete. It doesn't explain the return values, error conditions, or behavioral nuances, leaving gaps that could hinder an AI agent's ability to use the tool correctly in various scenarios.

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 parameter 'id' clearly documented in the schema as 'Memory ID to promote'. The description doesn't add any additional meaning or context beyond what the schema provides, such as format examples 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 tool's purpose with a specific verb ('promote') and resource ('memory's trust level'), and it explains the progression of states (hypothesis → active → validated). However, it doesn't explicitly distinguish this from similar sibling tools like 'update_memory' or 'supersede_memory', which might also modify memory 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?

The description provides clear context for when to use the tool ('when evidence confirms a memory is true'), which helps guide its application. However, it doesn't specify when NOT to use it or mention alternatives among the sibling tools, such as when to choose 'deprecate_memory' or 'update_memory' instead.

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 token budgeting and context loading, but lacks details on permissions, rate limits, error handling, or what 'most relevant' means algorithmically. For a tool with no annotations, 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 two concise sentences that are front-loaded with the core purpose. Every word earns its place, with no redundancy or fluff, making it highly efficient 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 moderate complexity (2 parameters, no output schema, no annotations), the description is minimally adequate. It covers purpose and usage but lacks details on behavior, parameter semantics, and output, leaving gaps that could hinder effective use by 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?

The input schema has 2 parameters with 0% description coverage, so the schema provides no semantic information. The description adds some meaning by implying 'query' is for a topic and 'max_tokens' controls output size, but it doesn't explain parameter formats, constraints, or interactions. This partial compensation justifies a baseline 3.

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's purpose: 'Get the most relevant memories for a topic, fitted to a token budget.' It specifies the verb ('Get') and resource ('memories'), with additional context about token budgeting. However, it doesn't explicitly differentiate from siblings like 'search_memory' or 'list_memories', which limits the score to 4.

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 clear usage context: 'Use at the start of a task to load context.' This gives a specific when-to-use guideline, but it doesn't mention when not to use it or name alternatives among the many sibling tools (e.g., 'search_memory'), so it falls short of a perfect 5.

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. It describes the tool's behavior (saving state for later loading) and implies it's a write operation, but lacks details on permissions, error handling, or storage limits. It adds some context (e.g., automatic loading by next instance) but is incomplete for a mutation tool without 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 front-loaded with the core purpose and usage timing, followed by details on what to capture. Every sentence adds value: the first states the action and timing, the second specifies content, and the third explains the outcome. No wasted words, making it highly 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 no annotations, no output schema, and 2 parameters with 50% schema coverage, the description is moderately complete. It covers purpose, usage timing, and parameter semantics for 'summary', but lacks details on behavioral aspects like error handling and doesn't fully compensate for the missing parameter documentation for 'tags'.

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% (only 'summary' has a description). The description adds meaning by explaining what 'summary' should contain ('Capture: what's in progress, what's blocked, what's done, decisions made'), which clarifies beyond the schema's generic description. However, it doesn't address 'tags', leaving one parameter partially undocumented.

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 specific action ('Save current session state') and resource ('session state'), distinguishing it from sibling tools like 'load_session' (which loads) and memory tools (which handle different resources). It specifies what gets captured: 'what's in progress, what's blocked, what's done, decisions made', making the purpose explicit and differentiated.

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 states when to use this tool: 'before conversation ends or context compresses'. It also mentions the alternative ('The next agent instance loads this automatically'), though not by tool name. This provides clear context for usage versus not using it, aligning with the highest score criteria.

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 effectively describes key behavioral traits: it's a read-only search operation (implied by 'search'), specifies result ranking criteria ('relevance, trust status, and recency'), and mentions automatic exclusions ('deprecated and superseded memories are excluded automatically'). This adds valuable context beyond the input schema, though it could detail more on permissions or rate limits.

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 highly concise and well-structured, consisting of two sentences that efficiently convey purpose, behavior, and exclusions without any wasted words. It is front-loaded with the core functionality and follows with important behavioral details, making it easy to parse and understand 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, and no output schema, the description is largely complete. It covers purpose, behavior, and exclusions adequately for an agent to use the tool correctly. However, it could be more complete by mentioning the output format or any limitations, which would help compensate for the lack of 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?

Schema description coverage is 100%, so the input schema already documents all parameters thoroughly. The description adds minimal semantic value beyond the schema, as it doesn't explain parameter interactions or provide additional usage context for the parameters. The baseline score of 3 is appropriate since the schema does the heavy lifting, and the description doesn't compensate with extra insights.

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's purpose with specific verbs ('full-text search across all active memories') and distinguishes it from siblings by specifying scope ('active memories', 'deprecated and superseded memories are excluded automatically'). It explicitly identifies the resource being searched (memories) and the operation (search), differentiating from tools like list_memories or recall_memory.

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 stating it searches 'active memories' and excludes 'deprecated and superseded memories', which suggests when this tool is appropriate versus alternatives like list_memories. However, it doesn't explicitly state when to use this tool versus other search-related siblings or provide clear exclusions or prerequisites, leaving some ambiguity.

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 tool marks the old memory as superseded and links it to the replacement, but fails to address critical aspects like permissions needed, whether the operation is reversible, error conditions (e.g., invalid IDs), or rate limits, leaving 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 action ('Replace an old memory with a new one') and adds necessary detail ('Old memory is marked superseded and linked to the replacement') without any wasted words.

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 a mutation tool with no annotations and no output schema, the description is incomplete. It lacks information on behavioral traits (e.g., side effects, error handling), usage context relative to siblings, and output details, failing to compensate for the missing 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?

Schema description coverage is 100%, so the schema already documents both parameters ('old_id' and 'new_id'). The description adds no additional meaning beyond what the schema provides, such as format details or constraints, meeting 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 specific action ('Replace') and resource ('an old memory with a new one'), distinguishing it from siblings like 'update_memory' or 'deprecate_memory' by specifying the superseding and linking behavior.

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 'update_memory' or 'deprecate_memory', nor does it mention prerequisites such as needing existing memory IDs. The description implies usage but lacks explicit context 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 the full burden of behavioral disclosure. While it mentions that tags 'replaces existing tags' (implied from schema), it lacks critical details such as required permissions, whether updates are reversible, error handling for invalid IDs, or mutation side effects. 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 two sentences, front-loaded with the core purpose and followed by usage guidelines. Every sentence earns its place by adding value—no redundancy or waste. It is appropriately sized for the tool's complexity.

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 (mutation with 5 parameters), no annotations, and no output schema, the description is partially complete. It covers purpose and usage well but lacks behavioral details like error responses or side effects. It is adequate as a minimum viable description but has clear gaps in 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 schema description coverage is 100%, so the schema already documents all 5 parameters thoroughly (e.g., ID as required, title max length, confidence range). The description adds minimal value beyond the schema by listing updatable fields but does not provide additional syntax, format, or contextual details. 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 verb 'update' and the resource 'existing memory', specifying the exact fields that can be modified (title, content, tags, confidence). It distinguishes this tool from siblings like 'add_memory' (create new), 'delete_memory' (remove), and 'deprecate_memory' (mark obsolete), making the purpose specific and differentiated.

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 states when to use this tool: 'when a rule changes, a fix gets refined, or new context applies to an existing memory.' This provides clear context for usage, helping the agent decide between this and alternatives like 'add_memory' for new entries or 'deprecate_memory' for obsolete ones.

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