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

With no annotations, the description carries the full burden. It explains the grouping mechanism ('based on semantic similarity if embeddings are enabled'), the return type ('List of clusters or duplicate pairs with scores and suggested actions'), and error behavior ('Raises ValueError'). However, it does not disclose whether the operation is read-only or might trigger side effects, leaving some ambiguity for an 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 well-structured with a brief summary followed by Args/Returns/Raises sections. It is front-loaded with the main purpose. While it is a bit verbose, each section serves a purpose and no filler text is present.

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 (5 optional params, no output schema description), the description covers the key aspects: purpose, parameters, return value, and exceptions. The existence of an output schema fills the need for return structure details. It lacks detailed usage scenarios or edge cases, but overall it is complete enough for an agent to effectively invoke it.

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

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

Schema coverage is 0%, but the description compensates thoroughly. It explains each parameter with added context: strategy is 'Clustering strategy', threshold is 'Similarity threshold for linking (0.0-1.0, uses config default if not specified)', max_cluster_size is 'Maximum memories per cluster (1-100, uses config default)', find_duplicates changes behavior, and duplicate_threshold has its own range. This provides clear semantic meaning beyond the raw schema.

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

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

The description clearly states the tool's function: 'Cluster similar memories for potential consolidation or find duplicates' and 'Groups similar memories based on semantic similarity'. This is a specific verb+resource with useful context. However, it does not explicitly distinguish itself from the sibling tool 'consolidate_memories' or 'search_memory', so it falls short of 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 notes it is 'Useful for identifying redundant memories', which implies a use case. However, it provides no explicit guidance on when to use this tool versus alternatives, nor does it mention any exclusions or prerequisites. This is adequate but not thorough.

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 details the merging algorithm (content, tags, strength, timestamps), the preview vs apply behavior, and error conditions. It does not explicitly state whether original memories are deleted or modified in place, but overall transparency is high.

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-organized with clear sections: numbered merge steps, a mode list, parameter explanations, and returns/raises. Every sentence serves a purpose, and the initial purpose statement is front-loaded, making the tool easy to scan and understand.

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 (multiple modes, optional auto-detection, threshold validation, and different outputs for preview vs apply), the description covers all necessary aspects. It even documents return behavior and errors despite having an output schema. No material gaps remain.

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

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

Schema description coverage is 0%, so the description must compensate. It does so comprehensively: every parameter (mode, cluster_id, auto_detect, cohesion_threshold) is explained with defaults, valid range, and mode-specific requirements. This fully compensates for the absent schema-level descriptions.

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 opens with 'Consolidate similar memories using algorithmic merging,' a specific verb+resource phrase that clearly states the tool's purpose. However, it does not explicitly distinguish this tool from its sibling 'cluster_memories,' so it falls short of full 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 explains operational modes ('preview' and 'apply') and auto-detection, giving clear invocation context. It does not, however, state when to use this tool over alternatives like 'cluster_memories' or mention exclusions, leaving the choice to the agent based on implied semantics.

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 must carry the transparency burden. It discloses that invalid inputs raise ValueError and describes the return value, which is helpful. However, it does not mention whether memories must already exist, whether the relation is directed, or any side effects like duplicate handling, leaving important behavioral traits undisclosed.

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 Args, Returns, and Raises sections. The first two sentences are somewhat redundant ('Create an explicit relation' and 'Links two memories with a typed relationship'), but the rest is efficient and clearly formatted, earning a high but not perfect score.

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 relatively simple create-relation tool, the description is fairly complete: it covers all five parameters, allowed relation types, validation behavior, and what is returned. However, it omits preconditions like whether the referenced memories must exist, and lacks any statement about permissions or idempotency, which would fully round out the 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 0%, so the description fully compensates by explaining each parameter: source/target IDs as valid UUIDs, allowed relation_type values (related, causes, supports, contradicts, has_decision, consolidated_from), strength range 0.0-1.0, and metadata as additional relation info. This adds significant meaning beyond the bare 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 explicitly states 'Create an explicit relation between two memories' and 'Links two memories with a typed relationship,' using a specific verb and resource. It clearly differentiates from sibling tools like save_memory or consolidate_memories by focusing on relation creation.

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

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

The description implies when to use the tool (creating relations) but does not explicitly mention alternatives or exclusion criteria. It provides no guidance on when to choose this over other memory-related tools, leaving usage context implicit.

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?

The description explains that memories are removed or archived based on decay score and describes dry_run and archive_instead parameters. However, it does not disclose that dry_run defaults to true, so a bare call would not actually modify memories despite the description's active phrasing. This is a significant behavioral nuance given there are no annotations to provide safety hints.

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-organized with separate sections for summary, args, returns, and raises. It is concise, with no redundant sentences, and every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers purpose, parameters, return values, and error conditions, which is sufficient for a tool with an output schema. However, it lacks explicit notes on the default behavior of dry_run and the permanence of deletion, leaving some operational context unclear.

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 no descriptions, but the tool description fully defines each parameter: dry_run ('Preview what would be removed'), archive_instead ('Archive memories instead of deleting'), and limit ('Maximum number of memories to process'). It also documents the return type and ValueError, adding semantic meaning beyond the bare 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 'Perform garbage collection on low-scoring memories' and explains it removes or archives memories below a threshold. This specific verb+resource distinguishes it from siblings like search_memory or promote_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 context by stating that GC 'prevents the database from growing indefinitely with unused memories,' indicating when it should be used. However, it does not explicitly compare to alternatives like consolidate_memories or promote_memory, so it lacks explicit when-not-to-use 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?

No annotations are provided, so the description must disclose behavior. It states that the tool 'Get's' metrics and returns a dictionary of statistics, implying read-only behavior, but does not explicitly confirm side effects or whether metrics are cumulative. This is minimal but adequate for a getter.

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 action, and includes a return type note. No 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 tool has no parameters and an output schema exists, the description covers the core purpose well. However, it lacks any mention of how this relates to reset_performance_metrics or what specific metrics are included, so a perfect score is not warranted.

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?

There are zero parameters, so the description needs no parameter information. The schema has no properties, and the description adds no parameter details, which is appropriate. Baseline for 0 params is 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 uses the specific verb 'Get' and identifies the resource as 'current performance metrics and statistics', clearly distinguishing it from sibling reset_performance_metrics and other memory tools. The purpose is 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 performance metrics are needed, but does not explicitly mention alternatives or exclusions. It does not reference the sibling reset_performance_metrics, leaving the user to infer the distinction, but the context is clear enough.

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 fully discloses behavior: it states that results are paginated, explains page/page_size navigation, covers return fields (memories, not_found, pagination), and lists the ValueError for invalid IDs or exceeding 100 IDs. It also clarifies that include_relations and include_scores control relationships and decay scores/age, respectively.

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 labeled sections (Args, Returns, Examples, Raises) and front-loaded with the purpose. It is clear and efficient, though there is some redundancy (pagination is explained both in prose and in the Args/Returns sections), preventing a perfect conciseness score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is complete for a moderately complex tool: it explains input, output, pagination, error behavior, and provides examples. The presence of an output schema reduces the need to detail return values, but the description still covers the key fields. No prerequisites or exclusions are missing, and the tool's read-only nature is implied by 'retrieve'.

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

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

Schema coverage is 0%, so the description must add meaning. It does so comprehensively: every parameter (memory_ids, include_relations, include_scores, page, page_size) is described with its purpose, default (including the max 100 IDs constraint for memory_ids and max 100 for page_size). This goes well beyond the bare schema and compensates fully.

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 begins with a specific verb+resource: 'Retrieve specific memories by their IDs.' It also clarifies scope by referencing the reference MCP memory server's open_nodes functionality, which helps distinguish it from sibling tools like search_memory or save_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 clear context for when to use the tool (retrieving known IDs) and gives pagination examples, but it does not explicitly mention when to use an alternative or when not to use this tool. It lacks an explicit exclusion or alternative recommendation, making it a 4 rather than a 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?

With annotations absent, the description carries the full burden of behavioral disclosure. It discloses dry-run and force modes, explains that target is a storage format (not a file path) configured via LTM_VAULT_PATH, and lists ValueError conditions. It also specifies return values. It does not clarify whether promotion copies or moves memories, but provides substantial context overall.

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 front-loaded with a concise one-line purpose, followed by brief context, then organized Args, Returns, and Raises sections. Every sentence earns its place with no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers purpose, usage, parameters, returns, and error handling. Gaps include lack of clarity on whether memory_id and auto_detect are mutually exclusive and what happens when neither is provided. Since an output schema exists, return structure is covered, but default behavior remains ambiguous.

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

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

Schema description coverage is 0%, so the description must compensate. It does this thoroughly: memory_id is described as a valid UUID, auto_detect as automatic candidate detection, dry_run as a preview, target as a storage format with env var configuration, and force as overriding criteria. These details go well beyond the bare 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 opening line 'Promote high-value memories to long-term storage' uses a specific verb and resource, and the description clarifies the criteria ('high scores or frequent usage') and result ('become permanent'), clearly distinguishing it from sibling memory tools like save_memory or touch_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 clear context by explaining that memories with high scores or frequent usage are promoted, implying when to use the tool. However, it does not explicitly name alternative tools or state when not to use it, so it falls just short of a 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?

With no annotations provided, the description carries full responsibility for behavioral disclosure. It richly explains pagination, the relationship between page and page_size, the fact that relations are not paginated, error conditions (ValueError), and the optional inclusion of decay scores and age. This goes well beyond a simple read 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 well-structured with clear sections (description, pagination, args, returns, examples, raises) and front-loaded with a one-sentence purpose. Despite its length, every section adds value and the formatting makes it easy to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers all aspects needed for correct invocation: parameters, pagination behavior, return structure, and error handling. Even though an output schema exists (so return explanation isn't required), the description goes further by detailing the keys returned, which is helpful 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?

The input schema has 0% parameter description coverage, so the description fully compensates by explaining each parameter's meaning, allowed values, ranges, and defaults. It also provides examples showing parameter combinations.

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 opens with 'Read the entire knowledge graph of memories and relations,' a specific verb and resource that clearly distinguishes it from sibling tools like search_memory or cluster_memories. It also explicitly lists what is returned, reinforcing the tool's scope.

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 use, including pagination examples and a note to increment pages to see more results. However, it does not explicitly name alternatives (e.g., search_memory) or state when not to use this tool, so it falls short of a 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?

Annotations are absent, so the description carries full responsibility for behavioral disclosure. It only states the reset action and return value, but fails to disclose that this is a destructive, likely irreversible operation that clears all accumulated metrics. No mention of permissions, side effects, or safety 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 exceptionally concise: two sentences that get straight to the point. It front-loads the action and clearly states the return, with no 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?

For a zero-parameter tool, the description covers the core purpose and return type. However, it omits the destructive nature of the reset and any guidance on when to use it, making it incomplete for safe usage. The output schema may provide return details, but the missing side-effect warning is a significant 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?

There are zero parameters in the schema, so the baseline is 4. The description adds no parameter information, but none is needed since there are no 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 uses the specific verb 'Reset' with the resource 'all performance metrics' and notes that it returns confirmation. This clearly distinguishes it from the sibling 'get_performance_metrics' which is a read operation.

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, such as mentioning that it permanently clears data or suggesting using get_performance_metrics first. There are no alternatives or exclusions, 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?

With no annotations, the description fully discloses the tool's side effects: temporal decay ('will have temporal decay applied'), automatic forgetting ('forgotten if not used regularly'), and potential promotion to long-term storage. It also documents error behavior with 'Raises: ValueError.' These are significant behavioral traits that go beyond a simple save 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 structured efficiently: a one-sentence purpose, two sentences on behavior, a compact Args list, and a Raises clause. It avoids repetition and keeps the total length appropriate for a tool with six parameters, all of which are covered.

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, the description provides a complete picture: purpose, behavior, parameter details, and validation errors. Since an output schema exists, the lack of return-value documentation is acceptable. The only missing element is explicit alternative guidance, but that's captured under usage guidelines.

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 only specifies types and names, providing no descriptions for any parameters. The description compensates by explaining each parameter's semantic role (e.g., 'tags: Tags for categorization') and adding explicit constraints like 'max 50,000 chars' and 'max 50 tags, each max 100 chars.' This gives the agent concrete invocation requirements.

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 opens with 'Save a new memory to short-term storage,' using a specific verb ('save') and resource ('memory') with a clear target. It distinguishes from sibling tools like promote_memory and touch_memory by emphasizing creation and short-term placement. This unambiguous phrasing makes the purpose immediately obvious to an agent.

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 phrase 'short-term storage' sets clear context for when this tool is appropriate—creating a new memory intended for short-term use. However, it does not explicitly name alternatives or state when to avoid using this tool in favor of a sibling. It is more than implied guidance but lacks explicit exclusionary language.

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 fully carries the burden of behavioral disclosure. It explains the spaced-repetition blending ('Maslow effect'), pagination behavior, default values, return structure, and that ValueError is raised on invalid input. This goes far beyond what the schema or annotations provide.

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 clear sections (Args, Returns, Examples, Raises) and each sentence adds useful context. It is somewhat verbose, especially the multiple pagination examples, but the length is justified by the complexity of the 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?

The description is complete: it covers all 9 parameters, return data structure, pagination behavior, exceptions, defaults, and usage examples. The presence of an output schema does not need to be repeated, and the description adds everything needed for 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?

Although the schema has no per-parameter descriptions, the tool description explicitly explains every parameter's purpose, constraints, and defaults (e.g., 'query: Text query to search for (max 50,000 chars)', 'page_size: Number of memories per page (default: 10, max: 100)'). This adds substantial meaning beyond the bare schema definitions.

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 opens with a specific verb and resource: 'Search for memories with optional filters and scoring.' It clearly differentiates from sibling tools like search_unified by describing the unique 'Maslow effect' spaced-repetition blending behavior, making the tool's purpose immediately identifiable.

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 clearly explains when to use the tool — when searching memories with pagination and review blending. It provides detailed pagination instructions ('If a search term isn't found on the first page, increment page') and examples. However, it does not explicitly mention when not to use it or contrast with sibling tools like search_unified.

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 and does so admirably. It discloses pagination behavior, the structure of the returned dictionary, validation errors (ValueError), and the fact that results are unified across STM/LTM with ranking. This goes well beyond the schema and gives the agent actionable behavioral expectations.

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 clear sections (Pagination, Args, Returns, Examples, Raises). It front-loads the core purpose, then provides necessary detail without verbosity. Every sentence adds value, and the examples are illustrative without being redundant.

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 (9 parameters, no annotations), the description covers all practical aspects: what it does, when to paginate, parameter constraints, return format, example invocations, and error conditions. It is complete enough for an agent to invoke the tool correctly without additional 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 coverage is 0%, but the Args section compensates fully. It adds constraints not present in the schema, such as query max 50,000 chars, tags max 50, limit range (1-100), stm/ltm_weight ranges (0.0-2.0), window_days range (1-3650), and min_score range (0.0-1.0). The examples also clarify parameter usage in context.

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 first line 'Search across both STM and LTM with unified ranking' uses a specific verb (search), names both resources (STM and LTM), and highlights the unified ranking aspect. This clearly differentiates it from sibling search_memory, which likely targets a single memory type.

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 establishes clear context: this tool searches both STM and LTM, which implicitly guides when to use it. It also provides pagination advice ('increment page to see more results'). However, it does not explicitly name alternatives or state when not to use it, stopping short of full exclusion 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?

There are no annotations, so the description carries the full burden. It discloses the mechanism (updates last accessed time and use count), effects (resets decay, increases resistance), optional boost, return values, and error condition for invalid IDs. It does not mention permissions or side effects on other memories, but these are not critical for this 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 well-structured with a clear purpose statement, mechanism explanation, and clearly labeled Args/Returns/Raises sections. It is appropriately detailed without 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 the tool has only 2 parameters and an output schema, the description covers all essential aspects: what it does, how to use it, what it returns, and an error case. It provides enough context for an agent to select and invoke it correctly.

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

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

Schema description coverage is 0%, so the description must compensate. It provides explicit explanations for both parameters: memory_id as 'ID of the memory to reinforce (valid UUID)' and boost_strength as 'Whether to boost the base strength'. This adds meaning beyond the schema.

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

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

The description clearly states a specific action ('Reinforce a memory by updating its last accessed time and use count') and resource (memory), which distinguishes it from sibling tools focused on creating, searching, or consolidating memories.

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

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

The description explains when this tool is useful (to reset temporal decay and increase resistance to forgetting) and mentions an optional boost, but it does not explicitly contrast it with alternatives like promote_memory or provide exclusion conditions.

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