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 describes key features like 'meta-cognitive assessment,' 'hypothesis testing,' 'integrated graph-based memory system,' and 'session-based context management,' which gives useful context about the tool's capabilities. However, it doesn't address important behavioral aspects like whether this tool persists data, has rate limits, requires authentication, or what happens when invoked (e.g., does it store reasoning steps somewhere?). The description adds value but 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 well-structured with sections for key features, parameters, and usage guidelines, which helps organization. However, it's quite lengthy with redundant parameter explanations that duplicate schema content. The 'Enhanced Parameters' section is particularly verbose given the 100% schema coverage. Some sentences like 'Branching (inherited from sequential thinking)' could be more concise. The structure is good but the content could be more efficiently presented.

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 high complexity (21 parameters, no annotations, no output schema), the description provides reasonable context about the tool's purpose and features. However, it doesn't explain what the tool actually returns or produces (no output schema means the description should address this gap). For a sophisticated reasoning tool with many parameters, the description should more clearly explain the overall workflow and expected outcomes. It's adequate but has clear gaps for such a complex tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 21 parameters thoroughly. The description's 'Enhanced Parameters' section lists and briefly explains each parameter, but this mostly repeats what's in the schema descriptions without adding significant new meaning. For example, it states 'confidence: Self-assessment 0.0-1.0' while the schema says 'Confidence in this reasoning step (0.0-1.0)' - nearly identical. The description adds minimal value beyond the comprehensive schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states this is an 'advanced cognitive reasoning tool' for 'complex reasoning that benefits from self-reflection, systematic hypothesis development, memory of previous insights, and quality assessment.' It distinguishes from siblings by focusing on reasoning processes rather than memory/library management or JSON operations. However, it doesn't specify what resource it acts upon (e.g., 'processes reasoning steps' would be more specific).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use this tool: 'for complex reasoning that benefits from self-reflection and confidence tracking, systematic hypothesis development, memory of previous insights, and quality assessment of reasoning.' This gives clear context for application. However, it doesn't mention when NOT to use it or explicitly contrast with sibling tools (e.g., 'use query_reasoning_memory for retrieving past reasoning 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly indicates this is a creation/mutation operation and specifies naming constraints (letters, numbers, underscores, hyphens), which is useful behavioral context. However, it doesn't mention potential error conditions (e.g., duplicate names), permission requirements, or whether the operation is idempotent/reversible.

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 well-structured and appropriately sized with three focused paragraphs: purpose statement, usage context, and parameter/return information. Every sentence adds value with no redundancy or wasted words. The information is front-loaded with the core purpose stated first.

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 creation tool with no annotations and no output schema, the description provides adequate but incomplete context. It covers the basic operation, naming constraints, and return indication, but lacks details about error conditions, response format, or integration with sibling tools. The absence of output schema means the description should ideally provide more detail about what 'success status and message' entails.

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 fully documents the single parameter. The description repeats the parameter name and requirement but adds minimal value beyond what's in the schema. The naming constraint information is useful but doesn't significantly enhance understanding of the parameter's semantics beyond the schema's basic 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 tool's purpose with specific verb ('create') and resource ('new named memory library'), distinguishing it from sibling tools like 'list_memory_libraries' and 'switch_memory_library' which perform different operations on the same resource. It also specifies the function is for 'organized knowledge storage' and mentions different use cases (projects, domains, contexts).

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 about when to use this tool ('for different projects, domains, or contexts') and implicitly distinguishes it from sibling tools by focusing on creation rather than listing, querying, or switching libraries. However, it doesn't explicitly state when NOT to use it or name specific alternatives like 'list_memory_libraries' for checking existing libraries first.

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 that the tool creates a new file (a write operation) and returns success status, which covers basic behavior. However, it lacks details on permissions, error conditions, rate limits, or whether the operation is idempotent. The description doesn't contradict annotations, but it's insufficient for a mutation tool without annotation support.

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 appropriately sized and front-loaded, starting with the core purpose. The parameter list is organized but could be more integrated into the flow. Sentences are efficient, though the return statement is somewhat redundant given the schema coverage. Overall, it avoids unnecessary verbosity.

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 5 parameters with 100% schema coverage and no output schema, the description provides adequate context for a creation tool. It covers the action and parameters but lacks behavioral details like error handling or side effects. Without annotations, it should ideally include more about the mutation's impact, but it's minimally complete for basic 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%, so the schema already documents all parameters thoroughly. The description lists parameters with brief notes (e.g., 'required', 'optional'), but adds minimal semantic value beyond what's in the schema. It doesn't explain interactions between parameters or provide examples, 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 creates a new system JSON file for storing data or instructions, specifying the resource (system JSON file) and action (create). It distinguishes from siblings like list_system_json and get_system_json by focusing on creation rather than retrieval. However, it doesn't explicitly differentiate from create_memory_library, which might be a similar creation 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. It doesn't mention when to choose create_system_json over create_memory_library or other creation tools, nor does it specify prerequisites or exclusions. Usage context is implied through the tool name 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 provided, the description carries the full burden of behavioral disclosure. It implies a read-only operation ('Get information') but doesn't explicitly state if it's safe, requires permissions, has rate limits, or what happens if no library is active. The description adds some context about returned data but lacks critical behavioral details for a 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 concise and front-loaded, with the first sentence stating the core purpose. The second sentence adds useful details about returned data, and the third sentence is slightly redundant but not wasteful. Overall, it's well-structured and efficient, though minor trimming could improve it further.

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) and lack of annotations and output schema, the description is minimally adequate. It explains what the tool does and what data it returns, but it doesn't cover behavioral aspects like error handling or dependencies on an active library. For a simple tool, this is acceptable but leaves gaps in completeness.

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 zero parameters, and schema description coverage is 100%, so there's no need for parameter documentation in the description. The description appropriately doesn't discuss parameters, earning a high baseline score. It could be a 5 if it explicitly noted 'no parameters required,' but the current omission is acceptable.

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 ('Get information') and resource ('currently active memory library'), and it lists specific data returned (name, nodes, sessions, metadata). However, it doesn't explicitly differentiate from sibling tools like 'list_memory_libraries' or 'get_system_json', 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 when to prefer this over 'list_memory_libraries' (which might list all libraries) or 'get_system_json' (which might retrieve system data), nor does it specify prerequisites like requiring an active library. This leaves 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 states the tool retrieves data (implying a read-only operation) and describes the return format, but lacks critical details such as whether authentication is required, if there are rate limits, what happens if the file doesn't exist, or if the operation is idempotent. For a read 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 appropriately concise and well-structured, with a clear purpose statement followed by parameter and return details in separate lines. Every sentence adds value, and there's no redundant information. However, the lack of usage guidelines or behavioral context means it could be more comprehensive without sacrificing 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 simplicity (1 parameter, no output schema, no annotations), the description is adequate but minimal. It covers the basic purpose and return format, which is sufficient for a straightforward read operation. However, it misses opportunities to clarify usage relative to siblings or address potential errors, making it just barely complete enough for an agent to use correctly in ideal conditions.

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 'name' fully documented in the schema as 'Name of the system JSON file to retrieve'. The description repeats this information without adding meaningful context beyond what's in the schema, such as examples of valid names, format constraints, or how it relates to files listed by 'list_system_json'. This meets the baseline for high schema coverage but doesn't enhance 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 clearly states the tool's purpose with a specific verb ('Retrieve') and resource ('system JSON file by name'), making it immediately understandable. However, it doesn't explicitly differentiate from its sibling 'list_system_json' (which presumably lists files rather than retrieving content) or 'search_system_json' (which might search within files), leaving some ambiguity about when to choose this specific retrieval 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 like 'list_system_json' or 'search_system_json'. It mentions the required parameter but offers no context about prerequisites, error conditions, or typical use cases, leaving the agent to infer usage solely from the tool name and basic parameter info.

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 describes what the tool does (lists libraries with metadata) and the return format ('organized, searchable library information'), which adds value beyond the input schema. However, it doesn't cover important behavioral aspects like whether this is a read-only operation (implied but not stated), potential rate limits, authentication needs, or pagination behavior, leaving gaps for a mutation-free 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 efficiently structured: a clear purpose statement followed by bullet points for metadata details and a note on return format. Every sentence adds value without redundancy, and it's front-loaded with the core functionality. No wasted words or unnecessary elaboration, making it highly concise and well-organized.

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 output schema, no annotations), the description is reasonably complete. It explains what the tool does, what metadata it returns, and the nature of the output ('organized, searchable'). However, without an output schema, it could benefit from more detail on the exact return structure (e.g., JSON array format), but it adequately covers the essentials for a simple list operation.

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 focuses on output semantics, detailing the metadata fields returned (library name, number of memory nodes, last modified date). This adds meaningful context beyond the schema, justifying a score above the baseline of 3 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: 'List all available memory libraries with metadata.' It specifies the verb ('List'), resource ('memory libraries'), and scope ('all available'), distinguishing it from siblings like 'get_current_library_info' (which likely fetches a specific library) and 'switch_memory_library' (which changes context). However, it doesn't explicitly differentiate from 'list_system_json' or other list tools, keeping it at 4 rather than 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 implies usage by stating it 'Shows all existing memory libraries,' suggesting it's for retrieving a comprehensive list. However, it lacks explicit guidance on when to use this tool versus alternatives like 'get_current_library_info' (for current library) or 'query_reasoning_memory' (for querying content). No exclusions or prerequisites are mentioned, leaving usage context inferred rather than clearly defined.

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 that the tool returns a list with specific fields (names, domains, descriptions), which is useful behavioral context. However, it lacks details on potential limitations like pagination, rate limits, or authentication requirements, leaving gaps 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 concise sentences with zero waste: the first states the action and resource, and the second specifies the return format. It is front-loaded with the core purpose and efficiently structured, earning its place without 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?

Given the tool's simplicity (0 parameters, no output schema, no annotations), the description is mostly complete for a list operation. It explains what is returned, but could improve by addressing potential behavioral aspects like ordering or completeness of the list. However, it adequately covers the core functionality without being overly complex.

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% (though trivial since there are no parameters). The description does not need to add parameter semantics, so it meets the baseline of 4 for zero-parameter tools, as it appropriately focuses on output behavior instead.

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 ('List all available') and resource ('system JSON files'), distinguishing it from siblings like 'get_system_json' (likely retrieves one file) and 'search_system_json' (likely filters results). It explicitly mentions what information is returned (names, domains, descriptions), 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 implies usage when needing a comprehensive list of all system JSON files without filtering, as opposed to 'search_system_json' which likely allows filtering. However, it does not explicitly state when NOT to use this tool or name alternatives, missing full explicit guidance.

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 describes what the tool does (query memory system) and what it returns (related memories with confidence scores and connection information), which covers basic behavioral traits. However, it doesn't disclose important operational details like whether this is a read-only operation, potential rate limits, authentication requirements, or how confidence scores are calculated. The description adds value but 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 well-structured and appropriately sized. It begins with a clear purpose statement, follows with a bulleted 'Useful for' section that efficiently communicates use cases, includes a parameters section, and ends with return information. Every sentence earns its place, and the information is front-loaded with the most important details first. No wasted words 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?

Given the tool's complexity (querying a reasoning memory system with 2 parameters), no annotations, and no output schema, the description provides adequate but incomplete coverage. It explains what the tool does and when to use it, but lacks details about the memory system's structure, how results are ranked, what 'connection information' entails, or error conditions. The description is complete enough for basic understanding but leaves important contextual 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 schema description coverage is 100%, with both parameters well-documented in the input schema. The description adds a 'Parameters' section that restates what's already in the schema without providing additional semantic context. It doesn't explain what constitutes a valid session_id format, provide query examples, or offer guidance on query construction. Since the schema does the heavy lifting, 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 tool's purpose as querying an integrated memory system to find related insights, hypotheses, and evidence. It uses specific verbs ('query', 'find', 'retrieve', 'understand', 'build') and identifies the resource ('integrated memory system'). However, it doesn't explicitly differentiate this tool from sibling tools like 'search_system_json' or 'get_system_json', which appear to have similar search/retrieval functions.

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 'Useful for' section provides clear context about when to use this tool (finding similar problems, retrieving hypotheses/evidence, understanding connections, building on previous sessions). This gives strong guidance on appropriate use cases. However, it doesn't explicitly state when NOT to use this tool or mention alternatives among the sibling tools, which would be needed for a perfect score.

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 returns 'matching files with relevance scores,' which adds some context about output format. However, it lacks details on permissions, rate limits, error handling, or whether this is a read-only operation (implied by 'search' but not explicit). For a tool with zero annotation coverage, this is a significant gap in behavioral 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 appropriately sized and front-loaded, with the core purpose stated first. The two sentences are efficient, though the parameter section could be integrated more smoothly. There's no wasted text, but it could be slightly more structured (e.g., merging the parameter note into the main description).

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 one parameter), no annotations, and no output schema, the description is minimally adequate. It covers the basic purpose and output format but lacks details on behavioral traits, usage context, and parameter nuances. Without annotations or output schema, it should do more to be complete, but it meets the bare minimum for a simple search tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds minimal meaning beyond the input schema. It repeats the parameter name and its purpose ('Search query to find matching system JSON files'), which is already covered in the schema description (100% coverage). No additional details like query syntax, examples, or constraints are provided. With high schema coverage, the baseline is 3, and the description doesn't compensate with extra value.

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: 'Search through system JSON files by query.' This specifies the verb (search), resource (system JSON files), and mechanism (by query). However, it doesn't explicitly differentiate from sibling tools like 'list_system_json' or 'get_system_json', which might offer different approaches to accessing JSON files.

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 sibling tools like 'list_system_json' (which might list all files without search) or 'get_system_json' (which might retrieve a specific file), leaving the agent to infer usage context. There's no explicit when/when-not or alternative recommendations.

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 adds useful context about saving session state before switching, which is not obvious from the tool name alone. However, it does not cover other potential behavioral traits like error handling, permissions needed, or side effects, leaving gaps 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 appropriately sized and front-loaded, starting with the core purpose. It uses clear sentences without unnecessary fluff, though the parameter and return sections could be more integrated or concise, slightly affecting structure.

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 (state-switching operation), no annotations, and no output schema, the description is somewhat complete but has gaps. It explains the action and state-saving behavior but lacks details on return values (beyond a vague mention), error cases, or integration with sibling tools, making it adequate but not fully comprehensive.

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 input schema already fully documents the single parameter 'library_name'. The description repeats this information without adding significant meaning beyond what the schema provides, such as format examples or constraints, resulting in a baseline score of 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 action ('switch to a different memory library') and resource ('memory library'), making the purpose evident. However, it does not explicitly differentiate this tool from its siblings like 'list_memory_libraries' or 'get_current_library_info', which reduces the score from 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 implies usage by mentioning 'different contexts or projects' and that 'current session state is saved before switching', providing some context. However, it lacks explicit guidance on when to use this tool versus alternatives (e.g., when to switch vs. create or list libraries), leaving room for ambiguity.

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