GoldenMatch

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

The description discloses key behavioral traits: source='agent', trust=0.5, canonicalization of ID pair. However, it omits other important behaviors like error handling, duplicate handling, or permission requirements. With no annotations, the description carries the full burden and covers only basic aspects.

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?

Two sentences are concise and front-loaded with the main action. However, the structure could be improved by separating parameter descriptions from behavioral notes.

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 (7 parameters, no output schema or annotations), the description is incomplete. It lacks information on return values, error conditions, and relationship to sibling tools like get_corrections or agent_approve_reject.

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 only 29%, and the description adds meaning only for id_a/id_b (canonicalization). Other parameters like decision, dataset, reason, matchkey_name are not explained. The description does not compensate sufficiently for the low 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 adds a pair correction to Learning Memory, with specific details about source and trust setting. It distinguishes this from sibling tools like list_corrections by focusing on the write action and internal behavior.

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

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

No explicit guidance on when to use this tool versus alternatives like agent_approve_reject or human steward corrections. The implicit context (agent source, low trust) is present but not framed as a usage recommendation.

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 must disclose behavioral traits. It only says 'approve or reject' without indicating side effects, permissions required, idempotency, or what happens after the action. Critical information is missing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise—one sentence—but brevity comes at the expense of substance. While it is front-loaded with the action, it lacks structured information about parameters or usage, making it minimally adequate.

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 6 parameters (5 required), 0% schema coverage, no output schema, and no annotations, the description is severely incomplete. It does not explain the tool's context, return value, or parameter meanings, leaving the agent without essential information.

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%, but the description adds no meaning to any of the 6 parameters. It does not explain id_a, id_b, decision, decided_by, reason, or job_name. The tool name gives minimal hints, but the description fails to compensate.

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 action: approve or reject a review queue pair. The verb-resource combination is specific and unambiguous, but it does not explicitly distinguish from sibling tools like agent_review_queue or agent_compare_strategies.

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

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

No guidance is provided on when to use this tool vs alternatives. There is no mention of prerequisites, context, or exclusions. The description simply states the function without any usage 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?

No annotations and the description does not disclose any behavioral traits (e.g., read/write, return format, side effects). Complete lack of transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, but it is overly terse and lacks necessary detail. Conciseness is not helpful when it omits 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?

With no annotations, no output schema, and fully undocumented parameters, the description fails to provide enough context for correct usage.

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% and description does not explain 'file_path' or 'ground_truth'. Parameters are completely undocumented.

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

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

The verb 'compare' is vague; does not specify what 'ER strategies' means or what the output is. Siblings like 'agent_deduplicate' and 'find_duplicates' have clearer purposes, but this tool does not differentiate well.

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

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

No guidance on when to use this tool vs alternatives (e.g., 'analyze_data' or 'suggest_config'). No context 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?

No annotations are present, so the description must carry the burden. It only mentions 'run full ER pipeline' without disclosing side effects, prerequisites, or operational details (e.g., resource intensity, data modification).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, which is concise but overly short for a tool with two parameters and no output schema. It lacks necessary detail and 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 complexity (2 parameters, one nested, no output schema), the description is severely incomplete. It fails to explain return values, parameter usage, or the overall workflow.

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%, and the description does not explain either parameter (file_path, config). The agent gets no insight into what values to provide, especially for the nested config object.

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 a specific action 'Run full ER pipeline' with modifiers 'confidence gating and reasoning', clearly indicating it performs entity resolution. However, it does not differentiate from sibling tools like find_duplicates or agent_match_sources, which may overlap.

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

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

No guidance is provided on when to use this tool versus alternatives. With many sibling tools, explicit usage context is missing.

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 provided, so description carries full burden. Only states purpose, no disclosure of behavior (e.g., is it read-only, required permissions, return format). Minimal 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?

Single sentence with no wasted words. Front-loaded with the purpose.

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

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

Simple tool with one parameter and no output schema, but description fails to explain what 'explain' returns or what constitutes a cluster. Incomplete for a self-contained 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 0%. The description does not add meaning for the 'cluster_id' parameter or explain what a cluster is. No compensation for missing schema 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?

Clear verb 'Explain' and resource 'why records are in the same cluster'. Distinguishes from sibling 'agent_explain_pair' which likely focuses on pairs, but lacks differentiation from 'explain_match'.

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

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

No guidance on when to use this tool versus alternatives like 'explain_match' or 'get_cluster'. No when-not or prerequisites mentioned.

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 exist, so the description must carry the full burden. It only says 'explanation', implying a read operation, but does not explicitly state idempotency, side effects, authentication needs, or rate limits. The description is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely short (one phrase) but this is underspecification rather than conciseness. It lacks structure and does not earn its place as a minimal viable 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 has 4 parameters (including nested objects) and no output schema or annotations, the description provides almost no useful context. It fails to explain what the explanation contains, how it is generated, or what the parameters represent.

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%, meaning the input schema has no parameter descriptions. The tool description does not explain any of the four parameters (record_a, record_b, exact, fuzzy), leaving their meanings completely unclear.

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 'Natural language explanation for a record pair' indicates the tool generates an explanation, but it is vague and does not differentiate from sibling tools like 'explain_match' or 'agent_explain_cluster', which likely perform similar 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?

No guidance is provided on when to use this tool versus alternatives. There are no when-to-use or when-not-to-use instructions, and no mention of alternatives among the many sibling tools.

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

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

No annotations provided; description mentions 'intelligent strategy selection' but fails to disclose read/write nature, side effects, or operation details.

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?

Single sentence is concise but omits critical information; could balance brevity with completeness.

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?

With 3 parameters, nested objects, no output schema, and many sibling tools, the description is far too sparse to be 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 coverage is 0%; description adds no meaning to parameters, and the config object (nested) is completely unexplained.

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?

Description clearly states the tool matches two files and adds 'intelligent strategy selection', distinguishing it from siblings like find_duplicates or pprl_link.

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

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

No guidance on when to use this tool vs alternatives such as agent_compare_strategies or pprl_link; usage is implied but not explicit.

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 implies a read operation ('get') but discloses no other behavioral traits such as side effects, authentication needs, or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that immediately conveys the tool's purpose. There is no superfluous wording.

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 single parameter, no output schema, and no annotations, the description is severely incomplete. It fails to explain what 'borderline pairs' are, what 'job_name' means, or what the tool returns.

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% description coverage for the only parameter 'job_name', and the description does not explain it at all. No value is added 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 'Get borderline pairs awaiting approval' clearly states a verb and resource. It differentiates from sibling tools like agent_approve_reject and agent_compare_strategies, which focus on different actions.

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

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

No guidance on when to use this tool versus alternatives. It doesn't mention any prerequisites, context, or exclusion criteria.

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

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

No annotations provided; description carries full burden. It lists three actions but gives no details on side effects, required permissions, or error conditions. Minimal behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short sentence, which is concise but not sufficiently informative. It is not wasteful but does not fully earn its place with adequate content.

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 performs multiple tasks (profiling, domain detection, recommendation) and has no output schema, the description is incomplete. It lacks explanation of output format, prerequisites, or how to interpret results.

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 only parameter 'file_path' has no description in schema or description. Schema coverage is 0%, so description needed to explain expected format or constraints, but it does not. No added 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 states actions (profile, detect domain, recommend ER strategy) but lacks specificity. It does not differentiate from sibling 'profile_data' which likely performs similar profiling. The purpose is vaguely clear but not precise.

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

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

No guidance on when to use this tool versus alternatives like 'profile_data', 'scan_quality', or 'identify_conflicts'. The description does not provide context or exclusions.

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

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

No annotations are provided; the description discloses the return value (config, telemetry) and mentions 'committed' and 'negative_evidence / Path Y', but does not discuss safety, side effects, or prerequisites. Behavior is partly transparent but incomplete.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with focused content, front-loading the verb and resource. It is concise but could be slightly clearer by separating return components.

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?

Without output schema or annotations, the description lacks details on constraints, error cases, prerequisites, or side effects. Given 41 siblings, more context is needed to avoid confusion.

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 has 2 params with 0% description coverage. The description explains 'file_path' as a CSV path but provides no detail on 'constraints' (object type). This is insufficient for a low-coverage case.

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 runs AutoConfigController on a CSV and specifies what it returns (committed GoldenMatchConfig, telemetry). It differentiates from siblings like 'suggest_config' and 'pprl_auto_config' by being the programmatic equivalent of 'goldenmatch autoconfig'.

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 via 'Programmatic equivalent of goldenmatch autoconfig' but does not explicitly state when to use it over alternatives or when not to use it. Given many siblings, more guidance would improve clarity.

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?

Discloses it returns telemetry from the most recent call, but does not mention error handling for missing calls, idempotency, or side effects. With no annotations, the description carries the full burden but is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences, front-loaded with the core purpose. No unnecessary 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 simple telemetry retrieval with no parameters or output schema, the description provides the key information but references an external endpoint that may not be accessible to the agent. Adequate but not fully self-contained.

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?

No parameters, schema coverage is 100%. The description adds context about the data source and shape, meeting the baseline of 4 for zero-parameter tools.

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?

Clearly states it returns telemetry data from the most recent auto_configure or agent_deduplicate call, and mentions the JSON shape matches a web endpoint. However, it does not explicitly differentiate from sibling tools, though none are similarly named.

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?

Implies it should be used after auto_configure or agent_deduplicate, but provides no guidance on when not to use it, what to do if no prior call exists, or 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?

No annotations provided, so description carries full burden. It only states basic purpose without disclosing behavioral traits such as whether creation is destructive, overwrites existing domains, or requires special permissions. Missing side-effect information.

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?

Two concise sentences with clear action and examples. No fluff, front-loaded with purpose.

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

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

Given 7 parameters with nested objects and no output schema, description is too brief. Lacks explanation of what a domain extraction rulebook is, how signals work, or return values, leaving gaps 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?

Schema description coverage is 100%, so baseline is 3. Description adds minimal value beyond schema by loosely referencing 'patterns' but does not clarify parameters like signals, stop_words, or brand_patterns.

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?

Description clearly states the tool creates a custom domain extraction rulebook with specific verb 'Create' and resource 'domain extraction rulebook', and provides examples of domains (medical devices, automotive parts, real estate). It distinguishes from sibling tools like list_domains and test_domain.

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?

Description implies usage for defining patterns for a specific data domain but does not explicitly state when to use this tool versus alternatives or provide exclusions. Context is clear but lacks direct 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?

Description mentions per-field score breakdown but doesn't disclose read-only nature, permissions, or other behavioral traits. No annotations provided, so description carries burden but is minimal.

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?

Two concise sentences with front-loaded main purpose. 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?

No output schema provided; description says 'shows per-field score breakdown' but doesn't specify output format. Adequate for a simple tool but could be improved.

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 100% with descriptions for both parameters. Description does not add meaningful extra meaning beyond the schema 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?

Clearly states the verb 'explain' and resource 'why two records match or don't match'. Additional detail about per-field score breakdown sets it apart from sibling tools like 'agent_explain_pair'.

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

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

No explicit when-to-use or when-not-to-use guidance. Implies usage for understanding matching decisions but lacks alternatives or exclusions.

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

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

With no annotations, the description must disclose behavioral traits. It only states the basic function without mentioning side effects (e.g., file overwriting), required permissions, or how the file is created. The description is too brief to be transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no extraneous words. It is concise but could potentially include a brief context sentence without losing 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 simple tool with two parameters and no output schema, the description is adequate but lacks context about what 'matching results' refers to and how the export process works (e.g., overwrite behavior). Could be improved with minimal additional information.

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 covers both parameters with descriptions (format enum and output_path). The description adds no additional meaning beyond the schema, meeting the baseline for full 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?

Description clearly states the verb 'Export' and the resource 'matching results', specifying file formats (CSV or JSON). It differentiates from sibling tools like memory_export by focusing on 'matching results', but does not elaborate on what constitutes 'matching results'.

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

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

No guidance is provided on when to use export_results versus alternatives like memory_export. There is no mention of prerequisites, context, or when not to use this tool.

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 provided, so description must fully disclose behavioral traits. Only states it finds duplicates, no mention of whether it modifies data, required permissions, or side effects. Insufficient for safe invocation.

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?

Two concise sentences with no wasted words. Could be slightly more structured but is appropriately brief.

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?

Adequate for a simple query tool, but lacks description of return values or output format. With no output schema, agents may not know what to expect. Behavioral disclosure also minimal.

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 100% with descriptions for both parameters. Description reinforces the record parameter's meaning but adds no new semantics 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?

Description clearly states the tool finds duplicate matches for a record, which is a specific verb+resource. It mentions searching against the loaded dataset, distinguishing it from sibling tools like match_record or agent_deduplicate, though not explicitly.

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?

Provides basic guidance to provide field values, but lacks explicit when-to-use or alternative tools. No exclusions or prerequisites mentioned.

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

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

With no annotations, the description carries full burden. It discloses core behavior (scan and apply fixes) and output, but lacks details on side effects, whether original file is modified, permissions needed, or error conditions. The prerequisite is noted, but other behavioral traits are absent.

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 with two sentences: one for action and output, one for prerequisite. No unnecessary words, but could be more structured with separate sections for input/output. Efficient but leaves room for improvement.

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 the core function and a dependency, but given 4 parameters and no output schema, it lacks examples, error handling, or deeper context like when to choose fix modes. It is minimally adequate for a tool of moderate complexity.

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 overall context (output summary and manifest) but does not significantly enhance understanding of individual parameters beyond what the schema provides. For example, 'fix_mode' and 'domain' have explanations in 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 action ('Run GoldenCheck scan and apply fixes'), the resource ('CSV file'), and the output ('fixed data summary and a manifest'). It distinguishes from sibling tools like 'scan_quality' which likely only scans, and 'add_correction' which adds a single correction.

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 for fixing CSV files but does not explicitly state when to use this tool versus alternatives like 'scan_quality'. It mentions a prerequisite (pip install) but provides no when-not-to-use or comparative 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 must convey behavioral traits. It indicates a read operation but does not disclose potential performance implications of retrieving 'all member records', rate limits, or any side effects. The lack of safety or cost information is a gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise, consisting of one sentence with no redundant words. The verb and resource are front-loaded, making it efficient for an agent to parse.

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

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

Given the tool's simplicity and full schema coverage, the description provides core functionality. However, it lacks details on return shape (e.g., record format) or pagination, and without an output schema, the description could be more explicit about what 'all member records and their field values' 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?

The input schema covers 100% of parameters, with a clear description for cluster_id. The description adds no additional meaning beyond the schema, so it meets the baseline but does not enhance 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 action 'Get details' and the target 'specific cluster', specifying that it returns 'all member records and their field values'. This differentiates it from sibling tools like list_clusters, which likely returns summary info, though not explicitly stated.

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

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

No guidance is given on when to use this tool versus alternatives such as list_clusters or explain_cluster. The description does not provide context for appropriate usage scenarios or mention any exclusions.

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

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

With no annotations, the description carries full burden. 'Get' implies a read-only operation, which is consistent. However, no additional behavioral details (e.g., whether the record is computed on the fly, any prerequisites) are provided. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, concise and front-loaded with the core action. It is efficient but somewhat sparse.

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 many sibling tools and no output schema, this description is insufficient. It does not explain what the canonical record contains or how it differs from other cluster views, making it hard for an agent to decide 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?

The description adds no meaning beyond the input schema. While schema coverage is 100%, the description merely restates the purpose. It could have clarified the role of cluster_id, e.g., that it is the unique identifier for the cluster.

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 verb 'Get' and the resource 'merged golden (canonical) record for a cluster', making the purpose clear. However, it does not differentiate from siblings like get_cluster or identity_resolve, which may also retrieve cluster-related data.

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

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

No guidance is provided on when to use this tool versus alternatives such as get_cluster, identity_resolve, or match_record. The description lacks any context for selection.

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

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

No annotations are provided, so the description carries the full burden. It implies a read-only operation but does not state side effects, permissions, or what happens if the dataset is missing.

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?

A single, front-loaded sentence with no unnecessary words. Every word contributes to understanding the tool's purpose.

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

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

Given no parameters and no output schema, the description partially compensates by naming the returned statistics. However, it lacks format details or behavior for edge cases, which would be expected for a complete picture.

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 no parameters, so the schema is fully covered. The description adds value by listing the statistics returned, which goes beyond the empty input 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 uses a specific verb 'Get' and resource 'dataset statistics', and lists the exact metrics returned (record count, cluster count, match rate, cluster sizes). This clearly distinguishes it from sibling tools like get_cluster or memory_stats.

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

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

No guidance on when to use this tool versus alternatives such as memory_stats or scan_quality. The description does not mention context or exclusions.

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

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

With no annotations provided, the description must fully disclose behavioral traits. It only states a 'list' action, which implies a read operation, but it does not confirm side-effect-free behavior, rate limits, authentication requirements, or what happens when no edges are found. The lack of transparency could lead to unsafe assumptions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, making it concise. However, it is under-informative for the complexity of the tool (with two optional parameters and a domain-specific concept). The structure is not front-loaded with critical details like parameter usage.

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 absence of an output schema and annotations, the description should provide more context about the domain (e.g., what 'evidence edges' are) and the effect of parameters. It is incomplete for a tool that operates in a complex identity resolution system with many sibling tools.

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

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

Schema description coverage is 0%, and the description does not mention the two parameters ('path' and 'dataset'). An AI agent has no way to infer their purpose or format from the description alone, requiring reliance on external knowledge or trial and error.

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 (list) and the specific resource (evidence edges marked 'conflicts_with'). It distinguishes the tool from siblings like 'identity_list' or 'get_cluster' by specifying the conflict condition. However, it does not provide further context to differentiate from related tools like 'explain_match' or 'get_cluster'.

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

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

No guidance is given on when to use this tool versus alternatives such as 'identity_list' or 'find_duplicates'. There is no mention of prerequisites, when not to use it, or what to do if no conflicts exist.

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

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

No annotations are provided, so the description carries full burden. It only states the basic purpose, omitting crucial behavioral traits such as whether the event log is append-only, pagination, ordering, or permissions required. Does not mention read-only nature or side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence. However, it sacrifices necessary detail for brevity. While efficient, it is under-informative for an agent to correctly invoke 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?

Given 3 parameters, no output schema, and no annotations, the description is severely incomplete. It lacks details on pagination limits, output format, event types, and how to specify the identity. An agent would likely misuse the tool 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 description coverage is 0%, and the description adds no meaning to the parameters (path, limit, entity_id). Not even a hint about which parameter corresponds to the 'identity' or what 'path' refers to. Fails to compensate for undocumented 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 action ('Return') and the resource ('temporal event log for an identity'). It distinguishes identity_history from sibling tools like identity_list (current state) or identity_merge (merge operation) by focusing on the log/history aspect.

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 vs alternatives. No context about prerequisites, scenarios where history is needed, or contrast with other identity tools that may return similar data.

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 should disclose behavioral traits like pagination (limit/offset), ordering, or authentication needs. It only states basic filtering, leaving critical behavior undocumented.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, which is concise but possibly under-specified. It front-loads the core purpose but omits important details, making it minimally acceptable.

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, 0% schema coverage, and no output schema, the description is incomplete. It fails to describe return format, pagination behavior, or ordering, which are essential for an agent to use the tool 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 coverage is 0%, so the description must compensate. It mentions filtering by dataset/status but does not explain other parameters like path, limit, or offset. The defaults for limit and offset are not clarified, and no enum values or format hints are provided.

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 'List identities' clearly states the action and resource, and the optional filtering by dataset/status provides context. However, it does not explicitly differentiate from sibling tools like identity_history or get_cluster, which also list identity-related data.

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 for listing identities with optional filters, but gives no guidance on when to use this tool versus alternatives like identity_conflicts or identity_merge. No when-not instructions or prerequisites are mentioned.

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?

Discloses the core effect (records transfer) but omits critical side effects: whether absorb_entity_id is deleted, reversibility, permissions, potential data loss, or what happens on failure. With no annotations, these gaps are significant.

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?

A single clear sentence that directly states the action and effect. No extraneous information, well-structured for quick parsing.

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?

Missing return value, error conditions, prerequisites, and irreversible behavior notes. For a potentially impactful operation like identity merge, the description is too sparse.

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?

Explains keep_entity_id and absorb_entity_id through the operation description, but fails to define optional parameters 'path' and 'reason'. Given 0% schema coverage, the description partially compensates but leaves gaps.

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

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

The description clearly specifies the verb 'merge' and the resource 'two identities', with precise detail about moving records from absorb to keep. This distinguishes it from siblings like identity_split or identity_resolve.

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

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

No guidance on when to use this tool versus alternatives (e.g., identity_resolve, agent_deduplicate). It lacks context on prerequisites or scenarios where merge is appropriate.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It states that the tool returns a full identity view or null, but does not mention side effects, permissions, or rate limits. It implies a read operation without explicitly confirming safety.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that efficiently communicates the tool's purpose and return value. There is no unnecessary information, and every word 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?

Given the lack of output schema and annotations, the description provides sufficient detail: it explains the tool's function, the format of the input (record_id), and the structure of the return value (members, evidence edges, recent events). It could be improved by mentioning potential errors or edge cases.

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

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

The input schema has 100% description coverage, so the baseline is 3. The description does not add significant meaning beyond the schema; it only restates the purpose. Parameter semantics are adequately covered by the schema alone.

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 that it resolves a record_id to its durable identity and specifies the return value (full identity view or null). It is a specific verb-resource combination, though it does not explicitly differentiate from sibling tools like 'identity_list' or 'get_golden_record'.

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

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

The description provides no explicit guidance on when to use this tool versus alternatives like 'identity_list' or 'get_golden_record'. It implies usage context (resolving to durable identity) but lacks when-not-to-use or prerequisite information.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It states the core behavior (original keeps remaining records) but omits details like reversibility, permissions, or side effects on related data, which are important for a split 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 a single, concise sentence that front-loads the action and outcome with no wasted words. It efficiently conveys the tool's purpose.

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

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

Given the complexity of a split operation with 4 parameters and no output schema, the description provides the basic outcome but lacks details on parameter usage, return format, and prerequisites. It is minimally adequate but incomplete.

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 explain parameters. It does not mention 'path' or 'reason', leaving their purpose unclear despite self-explanatory names for 'entity_id' and 'record_ids'. The description fails to compensate for the uncovered 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 splits a subset of records from an identity into a new identity, with the original keeping the remainder. This distinguishes it from sibling tools like identity_merge (which merges identities) and identity_resolve (which resolves conflicts).

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 this tool (to split records off an identity) but lacks explicit guidance on when not to use it or alternatives for similar tasks, such as merging identities. The context is clear but exclusions are absent.

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

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

With no annotations, the description carries the full burden. It discloses the trigger condition, return type, and empty-list behavior. However, it does not mention side effects (e.g., whether thresholds are updated in the DB) or if the operation is idempotent.

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?

Two sentences, front-loaded with the action and output, followed by a necessary precondition. Every word earns its place.

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

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

The description explains return values in detail, which compensates for the lack of an output schema. It covers the main behavioral condition. Could mention expected usage after add_correction, but not essential.

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 100% with descriptions for both parameters. The tool description adds no additional parameter info beyond what the schema provides, so baseline 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 it forces a MemoryLearner pass over accumulated corrections, with specific return values. This distinguishes it from siblings like add_correction (which adds corrections) and memory_stats (which reads memory status).

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

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

The description explicitly sets a precondition (>=10 corrections) and describes the fallback (empty list). It does not mention when to avoid using it or name alternatives, but the condition is clear enough for proper use.

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

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

No annotations are provided, so the description carries the full burden. It states the tool lists clusters and returns specific fields, which is transparent about output. However, it does not disclose any potential side effects, authorization needs, or behavior like pagination or ordering. The read-only nature is implied but not explicit.

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?

Two sentences with no wasted words. The first sentence states the primary purpose, and the second specifies return fields. Front-loaded and efficient.

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

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

Given the tool has two simple optional parameters and no output schema, the description is adequate but lacks context about typical usage, ordering, or how it fits into the deduplication workflow. With many sibling tools, more context would improve 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?

Schema coverage is 100%, with both 'limit' and 'min_size' having descriptions in the input schema. The description does not add meaning beyond the schema; it only describes output fields. Per guidelines, with high coverage baseline is 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 verb 'List', the resource 'duplicate clusters', and explicitly lists what is returned (cluster IDs, sizes, member counts). This distinguishes it from sibling tools like 'get_cluster' which returns a single cluster.

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 such as 'get_cluster', 'find_duplicates', or 'agent_explain_cluster'. There is no mention of prerequisites, usage context, or exclusions.

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

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

No annotations provided so description carries full burden. It lists return fields but omits side effects, permissions, or performance characteristics. Adequate but not detailed.

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?

One purposeful sentence plus a concise list of return fields. No wasted words, front-loaded with the action.

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 simplicity (2 optional params, no output schema), the description covers main behavior and return fields. Slight gap in usage context but largely 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 covers both parameters (path, dataset) with descriptions. The tool description does not add extra meaning beyond the schema, so baseline 3 applies.

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 lists stored corrections and optionally filters by dataset. It is distinct from siblings like add_correction. No ambiguity.

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

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

No guidance on when to use this tool versus alternatives (e.g., memory_export, get_stats). Lacks context for choosing filter or default behavior.

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 provided, so description carries full burden. Only states the basic listing function; no mention of read-only nature, performance, pagination, or side effects. Minimal disclosure beyond the obvious.

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?

Single sentence with no waste. Every word serves a purpose: action, resource, scope (built-in + user-defined).

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?

Lacks details on return format or what rulebook entries contain. Without output schema, agent may need more context. However, for a simple list tool, it is minimally 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?

No parameters exist, so schema coverage is 100%. Description adds no parameter info but none needed. Baseline for 0 params is 4, and description adequately conveys the tool's action.

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?

Description clearly states verb (list) and resource (domain extraction rulebooks) and distinguishes between built-in and user-defined. This differentiates from siblings like create_domain (creates) or test_domain (tests).

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?

Implied usage: use when needing to see available rulebooks. No explicit when/why not or alternatives provided, e.g., when to prefer this over get_cluster or profile_data.

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 covers basic behavior (real-time matching, using configuration) but does not disclose whether it is read-only, side effects, or return value format.

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?

Three concise sentences with a helpful example, all focused on the tool's purpose, 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?

Lacks explanation of return values or output format, which is relevant for a matching tool, but otherwise adequately covers the matching 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?

Schema covers all parameters, but description adds value with a concrete example for the record parameter and general mention of thresholds, going beyond the schema baseline.

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 matches a single record against the loaded dataset in real-time, distinguishing it from batch matching or analysis tools among the siblings.

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?

It implies usage for quick real-time checks of individual records, but does not explicitly state when not to use or directly name sibling 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?

No annotations are provided, so the description must disclose behavioral traits. It only describes a read operation but does not confirm it is non-destructive or disclose potential side effects, performance implications, or restrictions.

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 with no wasted words. It is front-loaded with the core purpose and adds necessary context about file writing responsibility.

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 the main output format and optional filtering, but given the lack of an output schema and the presence of many sibling tools, it fails to provide differentiation (e.g., from 'list_corrections') or edge-case behavior (e.g., empty results, limit handling).

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

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

Schema coverage is 50% (only 'path' has a description, which is already explicit). The description adds 'Optionally filter by dataset' but does not explain the format or allowed values of the 'dataset' parameter, leaving half of the parameters semantically undocumented.

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

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

The description clearly states it returns corrections as a list of dicts, with optional filtering by dataset. The verb 'return' and resource 'corrections' are specific, but it does not explicitly differentiate from the sibling tool 'list_corrections' which likely serves a similar 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 mentions the caller is responsible for writing the file, but provides no guidance on when to use this tool versus alternatives like 'list_corrections', nor any prerequisites or context-dependent usage.

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 states the tool is non-destructive and cheap, but does not discuss permissions, side effects, or potential errors. For a simple read operation, this is adequate but not exhaustive.

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 tool's purpose and key details. Every word is informative, and there is no redundancy or extraneous 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 simplicity (1 optional param, no output schema), the description covers purpose, key returned fields, and safety profile. It could mention the return format explicitly, but the listed fields provide sufficient clarity for an agent to understand what 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% for the single parameter (path), so the description does not need to add extra meaning. The description adds no further parameter details beyond the schema, which is acceptable given the high coverage.

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

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

The description clearly states the tool returns Learning Memory status with specific fields (total correction count, last learn time, current learned adjustments). It also highlights it is cheap and safe for status checks, distinguishing it from sibling tools that perform mutations or more complex analyses.

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 includes 'Cheap; safe for status checks,' which guides when to use it for lightweight health checks. It does not explicitly mention when not to use or list alternatives, but the context signals and sibling list imply no direct alternative for this specific status retrieval.

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 provided, so description carries full burden. It implies a non-destructive analysis but does not explicitly state read-only or safe behavior. Mentions LLM usage but no side effects.

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?

Single sentence, no filler, directly states purpose and outcome. Efficient and front-loaded.

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

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

Brief but covers core output. Lacks details on output structure, differentiation from siblings, and prerequisites. Adequate for a simple 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 coverage is 100% with clear descriptions. The description adds no extra meaning beyond the schema, so baseline 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 action ('analyze and recommend') and the resource ('PPRL configuration'). It specifies what is returned, distinguishing it from generic config tools like 'auto_configure'.

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

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

No guidance on when to use this tool vs alternatives (e.g., 'auto_configure', 'suggest_pprl'). Prerequisites like dataset loading are implied but not explicit.

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 mentions privacy-preserving behavior and bloom filters, which are key traits. However, it lacks details on computational costs, network requirements, error handling, or limitations. With no annotations, more behavioral context would be beneficial.

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 with two sentences, each providing essential information. No wasted words, and it front-loads the core purpose.

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

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

Given the tool's complexity (5 parameters, no output schema, no annotations), the description is incomplete. It does not explain what the tool returns, how to interpret results, or potential side effects. More detail on output and process is needed.

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 high (80%), and the schema already describes each parameter. The description adds minimal extra meaning beyond listing fields, threshold, and security level. Baseline score 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: 'Run privacy-preserving record linkage between two parties' data.' It specifies key aspects like computing bloom filters and matching without sharing raw data. Among siblings, this is the main execution tool, distinct from configuration tools like pprl_auto_config.

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 advises to 'Specify fields, threshold, and security level' but does not provide explicit guidance on when to use this tool versus alternatives like pprl_auto_config or suggest_pprl. Usage context is implied but not clearly delimited.

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

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

With no annotations, the description carries full responsibility. It explicitly states the return type (a data quality profile) and its components. While it does not disclaim side effects, the tool is clearly a read operation (no parameters, no destructive hint), and the description is transparent enough for an agent to understand its behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is front-loaded with the main action ('Get data quality profile') and efficiently lists the key outputs. Every word is necessary; there is no redundancy or fluff.

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

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

For a simple tool with no parameters and no output schema, the description adequately covers the return values. It provides enough detail for an agent to understand what the tool returns. However, it could be more complete by mentioning the source or format of the profile, but the lack of usage guidance is a minor gap.

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

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

The input schema has zero parameters, so the baseline is 4. The description adds value by detailing the output contents, which compensates for the lack of parameter guidance. The schema coverage is effectively 100%, and the description explains what the tool produces.

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

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

The description clearly states the action ('Get data quality profile') and lists the specific contents (column types, null rates, unique counts, sample values). It distinguishes itself from sibling tools like 'analyze_data' or 'scan_quality' by focusing on a predefined profile rather than general analysis or scanning.

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

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

No guidance is provided on when to use this tool versus its many siblings (e.g., 'scan_quality', 'analyze_data', 'fix_quality'). The description implies usage for obtaining a profile but does not give criteria for selection or mention alternative tools, leaving the agent to infer applicability.

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 explains that the tool normalizes and returns a manifest, but does not clarify whether the original file is modified or if output_path replaces it. While the core behavior is clear, some aspects (e.g., error behavior, idempotency) are omitted.

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?

Two sentences adequately convey the tool's purpose, operations, and requirement. The information is front-loaded with the verb 'Run'. A more structured format (e.g., bullet points for transforms) could improve scannability.

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

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

Given no output schema, the description explains the return value (manifest). Parameter semantics are covered, and the prerequisite is noted. The tool is simple, so completeness is adequate, though details on error handling or limitations are absent.

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 100%, but the description adds value by explaining that output_path is optional and omitting it returns a summary only. It also lists the types of transforms applied, providing context beyond the schema's basic 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 runs GoldenFlow data transforms on CSV files, specifying the exact normalizations (phone numbers, dates, etc.). This distinguishes it from sibling tools like fix_quality or profile_data.

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 mentions a prerequisite (pip install goldenmatch[transform]) but does not provide guidance on when to use this tool versus alternatives like fix_quality. Implicitly it is for normalization, but explicit when-not or alternative recommendations are missing.

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 tool only scans and does not apply fixes, and lists types of issues returned. However, it lacks details on error handling, permissions, or side effects (e.g., file modification status). Basic transparency is present but could be more comprehensive.

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: the first conveys action and output, the second adds a requirement. It is front-loaded, efficient, and contains no extraneous 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 no output schema, the description adequately explains the return (issues with types). It covers the core functionality, distinguishes from fix tools, and mentions a prerequisite. It does not address edge cases or error scenarios, but for a scanning tool, it is sufficiently 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 coverage is 100% and both parameters have descriptions. The description adds that the tool operates on CSV files, which is contextually useful but does not further clarify parameter values or usage beyond what the schema provides. Thus, it meets the baseline expectation.

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

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

The description clearly states the verb 'Run GoldenCheck data quality scan', the resource 'CSV file', and specific outcomes 'encoding errors, Unicode problems, format violations'. It distinguishes from sibling tools like 'fix_quality' by noting it returns issues without applying fixes.

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 indicates when to use (scanning data quality) and implies not to use when fixes are needed (since it says 'without applying fixes'). It also mentions a prerequisite (pip install goldenmatch[quality]). However, it does not explicitly list alternative tools or situations to avoid.

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 discloses the outcome (members become singletons) but lacks details on side effects, reversibility, permissions, or prerequisites. Since no annotations are provided, the description carries the full burden, and more transparency would be beneficial.

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 with two sentences, no wasted words. Front-loaded with the primary action.

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 simple tool with one parameter and no output schema, the description is functional but could mention reversibility or compare with siblings like identity_split to improve 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?

Schema coverage is 100% and the schema already describes the parameter adequately. The description adds no additional parameter 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 the action ('Break an entire cluster into individual records') and the result ('All members become singletons'). It uses a specific verb and resource, distinguishing it from similar tools like identity_split or unmerge_record.

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 context ('Use when a cluster is completely wrong'). However, it does not mention alternative tools or situations when not to use this tool.

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 provided, so the description must carry full burden. It states the tool suggests config changes via GoldenMatch, but does not disclose whether it mutates state, requires specific permissions, or other behavioral traits. Adequate but not exhaustive.

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?

Two sentences plus an example, with no fluff. The action is front-loaded and every sentence earns its place.

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

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

Given the single parameter and absence of output schema, the description adequately hints at the return value (suggested config changes). A more detailed output format would be ideal, but the example suffices.

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 100% and the description adds an inline example showing the expected format of bad_merges, clarifying the structure beyond the schema's generic description. This adds significant 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?

Clearly states the tool analyzes bad merges to suggest config changes, with a specific verb and resource. Distinguishes from siblings like auto_configure by focusing on learning from incorrect merges.

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?

Provides clear context: when you have bad merges and want to tighten thresholds. Does not explicitly list exclusions or alternatives, but the example strongly implies the use case.

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 fails to disclose any behavioral traits such as whether it modifies data, required permissions, or error handling. It only states it checks, but no details on side effects or constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very short but lacks important details, making it under-specified. Conciseness should not sacrifice completeness.

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 simplicity of the tool (one parameter, no output schema), the description should clarify the output or outcome of the check, but it does not. The context is insufficient for confident selection or 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?

The single parameter file_path has no description in the schema, and the description does not explain what file_path should represent or how it is used. The agent receives no additional semantic meaning.

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 checks if data needs privacy-preserving matching, which is a specific verb and resource. However, it does not distinguish from related sibling tools like pprl_auto_config or suggest_config.

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

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

No guidance on when to use this tool versus alternatives. The description does not mention any conditions or exclusions for usage.

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

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

With no annotations, the description carries full burden but only hints at non-destructive behavior ('Shows what features would be extracted'), lacking explicit statements about side effects or whether data is modified.

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?

Two sentences, front-loaded with purpose, no unnecessary words – concise and well-structured.

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

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

Lacks mention of prerequisites (e.g., domain must exist) and output format details; no output schema so description should compensate, but only offers vague 'shows what features would be extracted'.

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 100%, so baseline is 3. The description adds context but no new meaning beyond the schema's parameter 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 it tests a domain extraction rulebook against sample records and shows extracted features, distinguishing it from other domain tools like create_domain or list_domains.

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 (testing a rulebook) but does not mention when not to use or provide explicit alternatives among the many sibling tools.

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

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

No annotations provided, so description carries full burden. It discloses the re-clustering behavior after unmerge, but omits details like whether the record is deleted or just unlinked, and any permissions or side effects.

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?

Three sentences, front-loaded with the main action. Every sentence adds value: action, outcome, re-clustering detail, and usage guidance. No unnecessary 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 one-parameter tool with no output schema, the description covers the core behavior and re-clustering side effect. Lacks mention of reversibility or whether the record remains accessible, but overall adequate.

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 has 100% coverage with a clear description for record_id. Description adds no additional meaning beyond what the schema already provides, earning the baseline 3.

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

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

Description clearly states the verb (remove/unmerge) and resource (record from cluster). It specifies the outcome: record becomes a singleton and remaining members are re-clustered. This distinguishes it from siblings like 'shatter_cluster' which removes entire clusters.

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 says 'Use this to fix bad merges,' providing clear context for when to apply the tool. While it doesn't list exclusions, the context is sufficient given sibling tool names.

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