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

No annotations are provided, so the description carries full burden. It mentions 'auto-selects based on params' and the override capability, but doesn't disclose critical behavioral traits like what happens when multiple checks run, error handling, performance characteristics, or what 'health' assessment entails.

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?

Reasonably concise with two sentences plus a TIP. The first sentence is dense but informative. Could be slightly more front-loaded with purpose before implementation details.

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 3 parameters, 100% schema coverage, no output schema, and no annotations, the description provides good usage guidance but lacks behavioral context for a complex tool with 13 sub-tools. The absence of output schema means the description should ideally explain what results to expect.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds meaningful context about 'clear_state shares params with get_state — use this override to disambiguate' and mentions 'Multiple checks run if params match more than one tool,' which provides valuable semantic information 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 states the tool has '13 sub-tools' for health checks and can auto-select or override, but it's vague about what 'health' means in this context. It distinguishes from sibling 'context_loop' but doesn't clearly articulate the core purpose beyond being a collection of checks.

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?

Explicitly provides when-to-use guidance: 'prefer context_loop for comprehensive analysis, use context_health for targeted checks.' This clearly distinguishes from the sibling tool and gives specific usage context.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes the tool's behavior: it 'runs ALL context health checks,' 'auto-extracts facts,' 'detects contradictions,' 'checks answer quality,' and 'tells you exactly what to do next.' It also details the return structure ('directive' object with specific fields) and provides a minimal call example. However, it lacks information on potential side effects, error handling, or performance characteristics like 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 appropriately front-loaded with critical usage instructions, but it is verbose with some redundancy (e.g., repeating the tool's importance). Sentences like 'It is the single most important tool' and 'ESSENTIAL for:' could be more concise. While most content is valuable, the structure could be tighter to improve readability without losing essential information.

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

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

Given the tool's complexity (8 parameters, no annotations, no output schema), the description is fairly complete. It explains the tool's purpose, usage, behavior, and return structure in detail. However, it lacks an output schema, so the description must fully describe return values, which it does with the 'directive' object fields. Gaps include no error handling details and limited parameter semantics, but overall, it provides sufficient context for effective use.

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

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

The schema description coverage is high (88%), so the baseline is 3. The description adds minimal parameter semantics beyond the schema: it mentions 'most fields have smart defaults' and provides a minimal call example for 'messages.' However, it does not explain the purpose or interaction of parameters like 'sessionId,' 'claim,' or 'discoveryQuery,' nor does it clarify how parameters like 'currentInput' are 'auto-inferred.' The description compensates somewhat but not significantly.

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 ('runs ALL context health checks in one call') and resources ('auto-extracts facts from conversation, detects contradictions, checks answer quality'). It explicitly distinguishes this tool from its siblings by stating it 'replaces calling recap, conflict, ambiguity, entropy, grounding, drift, depth, and discovery tools individually,' making the differentiation 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 usage guidelines: 'CALL THIS TOOL every 2-3 turns and at the start of ANY task' and 'ESSENTIAL for: research tasks, multi-step workflows, long conversations, preserving context across turns, knowledge management, and any task requiring memory or fact-checking.' It also implicitly suggests when not to use it (for simpler tasks not requiring these features) and positions it as a replacement for multiple sibling tools, offering clear alternatives.

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 does an excellent job describing key behaviors: automatic file writing, internal chunk processing, blocking behavior until verification passes, separation of evidence capture from narrative approval, and file splitting for large batches. The only gap is lack of information about error handling or permission requirements.

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 in two sentences that each earn their place. The first establishes the core export functionality, while the second elaborates on the two distinct export modes. It's appropriately sized for an 8-parameter tool with complex behavior, though it could be slightly more front-loaded with the most critical 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 complex export tool with 8 parameters, no annotations, and no output schema, the description provides substantial context about what the tool does and how it behaves. It covers the two main export modes, automation aspects, and file handling. The main gap is lack of information about return values or error conditions, which would be helpful given the absence of an 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?

With 88% schema description coverage, the baseline is 3. The description adds meaningful context about parameter behavior: it explains that the tool 'can expand and write every verified report chunk' (relates to exportVerifiedReport), 'can also write every gathered raw-evidence batch even when verify has not passed yet' (relates to exportRawEvidence), and implies automation that affects multiple parameters. This provides valuable semantic understanding beyond the schema's technical 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 clearly states the tool's purpose with specific verbs ('writes research artifacts to disk', 'expand and write every verified report chunk', 'write every gathered raw-evidence batch') and distinguishes it from sibling tools by focusing on export functionality. It explicitly mentions automation capabilities that differentiate it from manual processes.

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

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

The description provides clear context about when to use the tool ('automatically writes research artifacts', 'without asking the LLM to loop finalize manually') and distinguishes between two export modes (verified reports vs raw evidence). However, it doesn't explicitly mention when NOT to use this tool or name specific alternatives among the 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'auto-selects based on params' which describes decision logic, and gives brief behavioral hints for each sub-tool (e.g., 'compress with integrity', 'knowledge graph with PageRank'). However, it doesn't disclose important behavioral traits like whether operations are read-only or destructive, performance characteristics, error handling, or authentication requirements.

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 poorly structured and contains unnecessary elements. It starts with '[MEMORY]' which adds no value, includes implementation details like 'use underscores' that don't help the agent, and has a confusing mix of tool documentation and usage instructions. The information about parameter mappings could be presented more clearly. Multiple sentences don't earn their place.

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

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

Given the complexity (6 sub-tools with different behaviors), no annotations, and no output schema, the description is incomplete. While it covers the basic action-parameter mappings, it doesn't explain what the tool returns, error conditions, or the semantics of operations like 'compact' or 'curate'. For a complex multi-function tool with no structured metadata, more comprehensive documentation would be expected.

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 baseline is 3. The description adds significant value by explaining the semantic mapping between 'action' values and required 'params' structures. For example, it specifies that 'store' requires {role, content}, 'recall' requires {query}, etc. This goes beyond what the schema provides by clarifying how parameters interact with actions.

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 lists the 6 sub-tools (store, recall, compact, graph, inspect, curate) which gives a vague sense of purpose, but it doesn't clearly state what the overall 'memory' tool does. It mentions 'hierarchical ingest', 'adaptive gate retrieval', etc., but these are technical terms that don't clearly explain the tool's function. The description focuses on implementation details rather than stating the core purpose.

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 specific actions: 'Auto-selects based on params or use 'action' to override.' It explains the default behavior (auto-selection) and how to override it. However, it doesn't provide guidance on when to use this tool versus its siblings (context_health, context_loop, etc.), 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?

With no annotations provided, the description carries full burden. It discloses the existence of 5 reasoning engines and auto-selection behavior, but doesn't describe performance characteristics, rate limits, authentication needs, or what constitutes successful/unsuccessful execution. The description adds some behavioral 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 appropriately sized with two sentences that efficiently convey the core functionality. The first sentence lists all engines, and the second explains the selection mechanism. No redundant information is present, though the engine names could be better integrated with their descriptions.

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 complex tool with 3 parameters (including a nested object), no annotations, and no output schema, the description is incomplete. It doesn't explain what the tool returns, error conditions, or provide examples of typical use cases. The parameter descriptions in the schema help, but the description alone leaves significant gaps for 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 baseline is 3. The description adds value by explaining the auto-selection logic ('Auto-selects based on params') and providing high-level descriptions of each method option, which complements the schema's technical enum values. However, it doesn't elaborate on how params influence auto-selection beyond what's implied.

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 provides reasoning with 5 different engines and auto-selection capability. It specifies the verb 'reasoning' and resource 'engines', but doesn't distinguish this from sibling tools like 'context_loop' or 'truthcheck' which might also involve reasoning processes.

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

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

The description implies usage through the mention of auto-selection based on params and method override, but doesn't explicitly state when to use this tool versus alternatives like 'context_loop' or 'truthcheck'. No specific exclusions or comparison to sibling tools is provided.

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 behavioral traits: autonomous file writing to disk during phases, quality gates (25K char/500 line min, 60% coverage requirement), phase dependencies (analyze blocked until coverage threshold), and critical workflow constraints (immediate gather after search). It explains operational mechanics like file persistence and phase chaining.

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 purpose and workflow but becomes verbose with repetitive instructions (e.g., multiple warnings about immediate gather). Some sentences could be condensed (e.g., overlapping explanations of file writing). It's informative but not optimally concise, with minor 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 (8 parameters, no annotations, no output schema), the description is highly complete: it explains the multi-phase process, behavioral constraints, file management, and integration with other tools. It compensates for lack of structured fields by detailing usage, dependencies, and outputs sufficiently for an agent to operate 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 high (88%), so baseline is 3. The description adds value by clarifying parameter usage in context: e.g., content's role per phase (init=task description, gather=write based on latest search), outputDir's purpose for autonomous file writing, and metadata conventions like targetSection for multi-gather accumulation. However, it doesn't fully detail all 8 parameters beyond schema hints.

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 orchestrates research tasks through 6 phases (init→gather→review→analyze→verify→finalize), specifying it structures, preserves, pressure-tests, and exports sourced findings. It distinguishes from siblings by focusing on research orchestration rather than isolated functions like export_research_files or 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?

Explicit guidance is provided: 'RECOMMENDED for research tasks,' with detailed workflow instructions (e.g., interleave web search and gather, do not batch searches, call phases in order). It contrasts with alternatives by noting it does not browse the web or invent source material, implying use of other MCP tools for sourcing.

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 and does well by disclosing key behavioral traits: the tool has three distinct sub-tools with different purposes, auto-selects based on parameters unless overridden, and describes what each sub-tool does (search, isolation, merge/discard). It doesn't mention performance characteristics like rate limits or error handling, but covers the core behavior adequately.

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 and well-structured: one sentence identifies the three sub-tools with their purposes, and a second sentence explains the auto-selection and override mechanism. Every word earns its place with no redundancy, and key information is front-loaded.

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

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

Given the tool's complexity (three sub-tools with different behaviors), no annotations, and no output schema, the description does an excellent job explaining what the tool does and how to use it. The main gap is lack of information about return values or error conditions, which would be helpful given the absence of output schema. However, for a sandbox tool with clear parameter guidance, it's mostly complete.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds significant value by explaining the semantic relationship between parameters: how 'action' overrides auto-selection, and how 'params' should be structured differently for each sub-tool (query for discover, name for quarantine, siloId+action for merge). This clarifies usage beyond the schema's technical 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 clearly states the tool's purpose: it's a sandbox with three specific sub-tools (discover, quarantine, merge) and explains their functions (semantic tool search, isolated state sandbox, merge/discard silo). It distinguishes from siblings by specifying its unique multi-action nature and auto-selection behavior, which none of the listed sibling tools appear to share.

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 each sub-tool: 'discover' for semantic search with query parameters, 'quarantine' for isolation with name parameter, and 'merge' for merging/discarding with siloId and action. It also explains the auto-selection logic and how to override it with the 'action' parameter, giving clear alternatives within the tool itself.

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 and does well: it discloses the tool's multi-method approach, auto-selection behavior, cascade functionality for correction, and scoring threshold (below 0.5 triggers correction). It explains the tool's operational logic beyond basic input-output, though it could mention performance characteristics or error handling more explicitly.

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 for a complex tool with 4 parameters and 7 methods. It front-loads the 7 tools list, then explains auto-selection and cascade behavior. While dense, every sentence adds value; it could be slightly more structured but remains efficient without 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's complexity (4 parameters, nested objects, 7 methods) and no annotations/output schema, the description does well: it covers purpose, usage modes, parameter effects, and behavioral logic. It explains the multi-tool approach and cascade correction, though it doesn't detail return formats or error cases, which would be helpful given the absence 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 baseline is 3. The description adds meaningful context: it explains that 'check' overrides auto-selection and lists what each enum value represents (e.g., 'probe — linguistic truth proxy signals'), providing semantic clarification beyond the schema's technical descriptions. It also explains the cascade parameter's effect, adding operational 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 explicitly states the tool's purpose: it performs truthfulness checking using 7 specific methods (probe, truth_direction, ncb, logic, verify_first, ioe, self_critique). It distinguishes itself from siblings by focusing on truth verification rather than context management, reasoning, or file operations. The description provides a clear verb ('truthfulness checking') and resource ('7 tools') with specific differentiation.

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

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

The description provides explicit guidance on when to use this tool: it mentions auto-selection of methods or manual override with 'check' parameter, and specifies cascade=true for auto-correction on low scores. It distinguishes usage scenarios between automatic and manual modes, though it doesn't explicitly mention when NOT to use it or alternatives among siblings, but the context is sufficiently clear for a complex tool.

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