Tollmint

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

No annotations exist, so the description carries the full burden. It discloses deterministic behavior, model-free nature, cost per call, and the output structure (per-sentence breakdown). It does not discuss auth or rate limits, but the provided details are extensive.

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 lengthy but every sentence adds value, front-loading the main purpose. It could be slightly more concise, but it remains efficient given the number of signals listed.

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 2 parameters, no output schema, and no annotations, the description provides a good overview but lacks parameter documentation. The per-sentence breakdown is mentioned but the exact output format is not specified.

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 describe the parameters 'text' or 'include_sentences' beyond the tool's purpose. The default value of 'include_sentences' is not mentioned, and maxLength/minLength for 'text' are not explained.

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 measures mechanicalness across 19 stylistic signals, provides a per-sentence breakdown, and explicitly distinguishes itself from sibling tools like 'design_ai-slop-detect' by clarifying it is not an AI detector.

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

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

The description explains it is deterministic and model-free, making before-and-after comparisons meaningful, and explicitly states it is not an AI detector. However, it does not directly guide when to use this tool versus its siblings beyond the 'not an AI detector' distinction.

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

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

With no annotations provided, the description fully takes on the burden of disclosure. It reveals that the tool returns a before/after analysis including burstiness, hedge/transition density, abstract-noun ratio, and specific mechanical sentences with triggered signals. It also states it reports failures rather than hiding them, and describes the cost structure. This is exceptionally 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 moderately long but each sentence contributes essential information: purpose, output details, limitations, cost. It is well-structured and front-loaded with the core purpose. A slight reduction could be made by omitting the cost detail, but it remains efficient for a complex tool.

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

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

Given the tool's complexity (rewriting with analysis, schema with 5 parameters, no output schema), the description covers nearly all necessary aspects: input requirements, output format (before/after analysis with specific metrics), behavioral traits (declines certain inputs, reports failures), and cost. It is complete enough 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?

The input schema has 5 parameters with 60% coverage (descriptions for voice, intended_use, reading_level). The description adds value by clarifying that intended_use is 'not the safeguard' and that text is subject to structural checks, not self-certification. It also explains that voice can be a profile from the brand-voice tool. This helps agents understand parameter semantics beyond schema.

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

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

The description clearly states the tool's purpose: rewriting text for tone, cadence, and brand voice while preserving meaning. It distinguishes from sibling tools like content_ai-score (which likely scores AI content) and design_ai-slop-detect (which detects AI slop). The verb 'rewrite' is specific and the resource 'text' is obvious.

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

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

The description explicitly states that the tool declines academic manuscripts and requests to defeat AI detection, providing clear when-not-to-use guidance. It implies the tool is for everyday content rewriting. However, it does not explicitly mention alternatives among siblings, though the context suggests a distinction from detection-focused tools.

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

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

With no annotations, the description provides good behavioral context: it is deterministic, model-free, reports template convergence not authorship, and states cost. However, it does not explain error handling or precedence when both url and html are provided.

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

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

The description is front-loaded with the purpose and is informative, though somewhat dense. It could be slightly more concise, but all sentences add 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, the description adequately explains what the tool returns (findings with quotes and moves). It covers complexity well, including cost and behavior.

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 the schema already describes each parameter. The description adds no additional semantics beyond the schema, meeting the 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's purpose: scoring a page against a specific AI/template design fingerprint. It lists concrete design elements and distinguishes itself from siblings by focusing on template detection.

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, nor any mention of when not to use it. The context for usage is implied but not stated.

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

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

With no annotations, the description carries full burden. It explicitly states the call costs nothing, no account or payment required, and outlines the type of data returned (laws, enforcement rows, defenses). This provides good behavioral context beyond what the schema offers.

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 one long paragraph packing many details; it front-loads the topic but is somewhat verbose. It could be more concise by splitting into sentences or bullet points while retaining all 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 6 parameters, no output schema, and no annotations, the description covers the scope of data, cost, and key details about the content. It lacks mention of pagination or sorting, but overall it is fairly complete for a retrieval 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 83%, so baseline is 3. The tool description does not add meaning beyond the schema's parameter descriptions (e.g., 'search' for free-text, 'dead_only' for non-live law). It provides general context but no extra parameter guidance.

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 covers accessibility duties and cases, listing specific laws and regimes (ADA, Section 508, European Accessibility Act, etc.), enforcement examples, and that it's free. This distinguishes it from sibling tools like legal_claims and legal_scraping.

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 the tool is for researching accessibility law, but it does not explicitly state when to use it versus alternatives, nor does it provide when-not or alternative tool names. Usage is implied by content alone.

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

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

No annotations are provided, so the description carries full burden. It discloses forward dates, dead rules (e.g., struck-down California laws), and notes that 'verified_only' may be blocked due to source restrictions. This is thorough and honest.

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

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

The description is front-loaded with the core purpose and concise, though it contains three sentences. It efficiently conveys essential information without redundancy.

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

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

Given the absence of an output schema, the description explains what each row contains (trigger, action, exemptions, penalty, enforcement). It covers all necessary context for a legal compliance tool, including edge cases like forward dates and dead laws.

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 83% (5 of 6 parameters have descriptions). The description does not add parameter-specific guidance beyond the schema, and the 'limit' parameter lacks a description. 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 tool provides binding obligations for disclosure, labeling, or watermarking of AI-generated content, citing specific laws and jurisdictions. It distinguishes itself from sibling tools by focusing on legal compliance rather than detection or design.

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 advises to 'Query before shipping generated content into a jurisdiction,' providing clear usage context. While it doesn't mention when to avoid using the tool, the purpose is sufficiently scoped, and the free nature is noted.

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 that the tool is free, requires no account, and describes output content. However, it does not explicitly state read-only behavior or rate limits, which are common for info retrieval tools. Still, transparency is good for a non-destructive data query tool.

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

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

Description is concise and well-structured: first paragraph lists covered topics and row structure, second addresses debunked rules and cost. Every sentence adds value, no redundancy. 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 no output schema, description adequately explains return structure (each row includes evidentiary standard, failure mode, enforcement). Also mentions additional debunked rules. Parameters are covered by schema. Complete enough for an agent to understand what it will receive, though lacking field names.

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 83% and parameters have descriptive names/schema descriptions. The tool description adds marginal value beyond schema by providing context on data coverage (e.g., claims types). It does not directly explain parameter semantics, but schema already does most of the work.

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's purpose: it provides information on which marketing claims legally require evidence and what evidence suffices, listing covered topics (superlatives, health, etc.) and row structure. This distinguishes it from siblings like legal_messaging and legal_ai-disclosure.

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 vs. alternatives. The description mentions that it's free and requires no account, but does not state when to prefer this tool over siblings like legal_messaging. Usage is implied from purpose, but lack of explicit exclusions or alternatives is a gap.

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 partially discloses behavioral traits by explaining the data returned and key concepts like consent_model. However, it does not explicitly state that the tool is read-only, mention error handling, or discuss rate limits, leaving some transparency gaps.

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

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

The description is front-loaded with the purpose but includes detailed legal explanations that could be condensed. While informative, it is somewhat verbose for a tool description, and every sentence does not earn 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 6 parameters and no output schema, the description provides substantial context about the tool's functionality, return contents, and jurisdictional nuances. It covers key aspects but lacks information on pagination or data freshness.

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 (83%), so baseline is 3. The description adds value for parameters like dead_only and verified_only by explaining their significance and default behaviors. The limit parameter lacks additional context, but overall the description enriches parameter understanding.

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

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

The description clearly states the tool's purpose: determining when commercial email, SMS, or calls may lawfully be sent, by channel and jurisdiction. It includes specific examples like consent_model and distinguishes from sibling tools by focusing on messaging legality.

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

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

The description provides clear context for usage, noting that the tool is free and requires no account or payment. It describes the content returned (opt-out deadlines, calling hours, etc.) but does not explicitly state when not to use it or suggest 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?

Since no annotations are provided, the description carries full burden for behavioral disclosure. It honestly notes limitations (Ninth Circuit is not US law) and states it's free with no account required. This adds transparency, though it omits mention of potential rate limits or data freshness.

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 detailed but efficiently packed with essential info. It front-loads the main purpose and uses examples to clarify scope. A minor reduction for length could improve conciseness, but it remains structured and helpful.

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 tool with no output schema and moderate complexity, the description covers scope, limitations, cost, and account requirements. It could mention result format or pagination, but overall it provides sufficient context 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 83%, so most parameters already have descriptions. The tool description does not add new meaning to parameters beyond what the schema provides. Baseline 3 is appropriate given 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 provides court holdings on scraping, crawling, and training-data acquisition. It gives concrete examples of questions it answers and specifies the perspective ('as an engineer asks'). This distinguishes it from sibling tools like legal_accessibility or legal_ai-disclosure which cover different legal topics.

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

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

The description provides context on when to use the tool (e.g., for scraping legality, EU exceptions, hiQ case history) but does not explicitly state when not to use it or offer alternative tools. However, the examples and scope make usage relatively clear.

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 key behavioral traits: the call is free, no account needed, and notes that the data includes vacated rules often wrongly believed live. However, it does not mention rate limits or pagination 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 concise single paragraph that front-loads the tool's purpose, then provides specifics. While not highly structured, it is efficient and avoids redundancy.

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

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

Given the tool's complexity with 6 parameters and no output schema, the description adequately covers the domain, including key exceptions and intent. It lacks details on return format and pagination but is otherwise complete for selection purposes.

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 83%. The description adds meaning beyond the schema by explaining that the data includes specific numbers (e.g., days for reminders, clicks for cancellation) and highlighting the dead_only filter's purpose. It enriches parameter understanding.

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

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

The description clearly states the tool provides rules on subscription sign-up, auto-renewal, cancellation, and total-price display across multiple jurisdictions, with specific numbers and a notable vacated rule. It distinguishes itself from sibling legal tools by focusing on subscription-specific regulations.

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 the tool is for querying subscription law rules and states it's free and requires no account, but it does not provide explicit guidance on when to use this tool versus alternatives or when not to use it.

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, description carries full burden. It states the call costs nothing and requires no account, signaling safe, read-only operation. However, does not mention rate limits or data sensitivity beyond that.

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 front-load key content and use cases. No redundancy; every sentence adds value. Appropriate length for a retrieval 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?

Complex tool with 6 parameters and no output schema. Description does not explain return format, pagination (though offset/limit exist), or how filters (domain, search, replication_status) affect results. Incomplete for agent to confidently invoke.

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 only 17% (one parameter documented). The description adds no meaning about parameters like limit, domain, offset, search, or replication_status. Agent left to infer from names 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 it provides cognitive biases with mechanism, triggers, countermeasures, and exploitation-risk score. It distinguishes itself from siblings like psych_heuristics and psych_dark-patterns by naming 'biases' 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?

Explicitly lists use cases: audit decision process, harden system, check reasoning. Also notes it is free with no account needed. Lacks explicit when-not-to-use guidance but context from siblings aids differentiation.

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

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

No annotations are provided, so the description carries full burden. It discloses deterministic behavior ('same markup always scores the same'), the algorithm (Hick's law weighting), and cost ($0.025 per call). This is good transparency, though it could add details about side effects or authentication needs.

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 four sentences that cover purpose, determinism, algorithm, and cost. No wasted words; well-structured 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?

The tool has 2 parameters, no output schema, and no annotations. The description explains what it measures and how it works, but does not describe the return value format or structure. For a measurement tool, this omission reduces 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 clear descriptions for url and html. The tool description adds no additional parameter meaning beyond what the schema provides. Baseline of 3 is appropriate.

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

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

The description starts with a clear verb and resource: 'Measure the mental effort a page demands before a decision can be made', and lists specific factors (form fields, choices, density, reading burden). It distinguishes itself from sibling psychology tools by focusing on cognitive load measurement.

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

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

The description provides context (e.g., deterministic, for tracking over time) but does not explicitly state when to use this tool versus alternatives like psych_biases or psych_dark-pattern-detect. No exclusions or alternative guidance is given.

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

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

With no annotations provided, the description fully bears the transparency burden. It discloses deterministic behavior, the lack of conversion lift prediction, cost per call, and details on what the tool checks (including regulatory exposure). No contradictions are present, and all behavioral traits are clearly stated.

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 yet comprehensive, with no wasted sentences. It front-loads the core purpose, then efficiently lists checks, caveats, and costs. Each sentence adds value, making it well-structured and appropriately sized.

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 (3 parameters, scoring with citations) and lack of output schema, the description is complete. It explains what the tool returns (scores with replication status, urgency flags) and its limitations, leaving no critical gaps for an agent to understand its capabilities.

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

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

Although schema coverage is 100%, the description adds significant meaning beyond the schema by explaining how each parameter is used (e.g., 'surrounding_text' for detecting unsupported urgency, 'context' for additional info). It details the logic behind the checks, which greatly aids the agent in providing relevant inputs.

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: scoring call-to-action text against a behavioral-science corpus. It lists specific checks (verb framing, friction words, etc.), making the verb and resource clear. While not explicitly distinguishing from siblings, its focus on CTA scoring is unique among the listed psych tools.

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

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

The description provides clear context on when to use the tool (for scoring CTAs) and explicitly states what it does not do ('Does not predict a conversion lift'), serving as a when-not. However, it does not name alternative tools or provide explicit exclusions, so it stops short of a 5.

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

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

The description discloses critical behavioral traits: it is fully deterministic ('no model call'), reproducible, costs $0.03 per call, and returns a clean/review/fail verdict. It also notes that patterns requiring full user flow are identified. However, it does not mention any limitations such as static-only analysis or error handling, which are not covered by annotations (none provided).

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 paragraph that front-loads the main purpose and efficiently covers key details like determinism, cost, and verdict. It is slightly verbose but every sentence adds value.

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

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

Given the lack of an output schema and the tool's moderate complexity, the description covers essential aspects: input sources, output (patterns with evidence/regulation/alternative), verdict, and cost. It mentions needing full user flow for some patterns. However, it does not describe error conditions or the exact format of returned data.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds context by explaining the verdict system and the overall function, but it does not enhance the understanding of individual parameters beyond what the schema already provides.

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: 'Scan a live page or raw HTML for deceptive design.' It specifies the action (scan), the resource (page/HTML), and the outcome (detect deceptive patterns with evidence, regulation, and alternative). This distinguishes it well from siblings like 'psych_biases' or 'content_ai-score'.

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

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

The description implies usage context through features like deterministic results and cost, but it does not explicitly state when to use this tool versus its sibling 'psych_dark-patterns' or other alternatives. It mentions verdicts suitable for deployment gating but lacks direct guidance on when not to use it.

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 carries the full burden. It discloses that the call is free, requires no account/payment, and describes the return content (regulations, signals, severity, alternative). It does not mention rate limits or side effects, but as a read-only taxonomy lookup, those are unlikely to be critical.

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 with no wasted words. The first sentence defines the tool, the second gives usage context, the third covers cost/auth. Front-loaded with essential information.

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

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

Given no output schema, the description adequately explains the return value (regulations, signals, severity, alternative). It covers two of four parameters implicitly (jurisdiction, severity), but misses 'search' and 'category'. For a taxonomy lookup, this is reasonably complete.

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

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

Schema description coverage is only 25% (only 'jurisdiction' has a description). The description does not elaborate on 'search', 'category', or 'min_severity' beyond what the schema provides. It implies jurisdiction and severity via 'regulations' and 'severity score', but leaves gaps for the other parameters.

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

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

The description clearly defines the tool as a 'deceptive-design taxonomy' listing regulations, signals, severity, and honest alternatives. It specifies use cases ('before shipping conversion changes' or 'to audit a competitor'), distinct from sibling tools like psych_dark-pattern-detect which likely focus on runtime detection.

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 explicit when-to-use guidance ('Use before shipping conversion changes, or to audit a competitor') and reinforces no cost or auth requirements. Does not explicitly state when not to use or compare to specific alternatives, but the context is clear enough for most agents.

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

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

No annotations are provided, so the description carries full burden. It discloses that effects with failed replication are included (not hidden), how to filter them, and confirms the tool is free with no payment or account needed. This gives the agent clear behavioral expectations.

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

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

Four sentences, each purposeful: purpose, content details, filtering note, and cost/access. No redundant or vague phrasing. The description is efficiently front-loaded with the verb and resource.

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 partially describes what the result contains (citation, replication status, effect size, boundary conditions). It explains key filtering but not pagination or default behavior. For a query tool with 7 optional parameters, the description provides adequate but not exhaustive 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 only 29% (2 of 7 params have descriptions). The description adds context for actionable_only (explains it excludes effects needing human review) but does not elaborate on domain, search, replication_status, limit, or offset. The parameter names and schema enums provide some clarity, but the description could more fully compensate for the low 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 'Query a curated corpus of behavioural science effects,' specifying both the action (query) and the resource (effects). It lists key attributes like canonical citation, replication status, effect size, and boundary conditions, which distinguishes it from sibling tools like psych_biases or psych_heuristics.

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

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

The description explains that the tool is free and requires no account, and advises using actionable_only to filter out contested/failed replications. However, it does not explicitly state when to choose this tool over similar sibling tools (e.g., psych_biases) or provide 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?

With no annotations, the description fully discloses behavior: it is a read-only query ('Free — this call costs nothing. No account or payment required'), covers patterns never enforced, and excludes cases lacking primary sources. 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 longer but every sentence adds necessary detail (inclusions, exclusions, free access). It is front-loaded with the core function, then elaborates. Could be slightly trimmed but 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?

No output schema, but the description explains return data composition (law, company, penalty, screen content) and includes excluded cases and unenforced patterns. Missing pagination or format details, but adequate for a list function.

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 80%, so baseline is 3. The description does not add meaning beyond the schema's parameter descriptions (e.g., enum values for outcome, pattern taxonomy ids). No extra semantic 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 specifies the verb 'regulatory enforcement actions' and the resource 'deceptive interface design', listing what each record includes (regulator's document, law, company, penalty, screen content). It distinguishes from sibling tools like psych_dark-patterns by focusing on enforcement outcomes including dismissals and findings of lawfulness.

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?

States 'Use to tell whether a design choice has cost anyone money, and where', and explains inclusions/exclusions (e.g., fine-only lists omit boundary rulings). While it lacks explicit when-not-to-use, the context is clear enough for an agent to infer appropriate use vs. other 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 the description carries the burden. It mentions the call is free and no account required, implying no side effects or costs. However, it does not explicitly state that the tool is read-only or describe any behavioral aspects beyond being free.

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 no superfluous words. It front-loads the core topic and key differentiators. Every sentence adds value.

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

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

Given the parameter count of 2, no output schema, and 0% schema coverage, the description is insufficient. It does not explain the return format, what the output contains (e.g., full list or filtered), or how to use the parameters effectively. The tool's simplicity suggests more could be provided.

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

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

Schema description coverage is 0%, so the description must compensate. The description mentions specific heuristics (Fitts, Hick, etc.) but does not explain how the 'search' or 'with_formula' parameters work. For instance, it's unclear if 'search' filters by heuristic name or concept, and what 'with_formula' does. The description adds minimal value over 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 it provides interaction-design laws with formulae, sources, and design implications, and explicitly distinguishes from the effects corpus. The tool name 'psych_heuristics' aligns with this purpose. However, the description is more about content than the action the tool performs (e.g., retrieve or list).

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 separates this tool from the effects corpus, stating 'these are engineering constraints, not contested empirical claims,' which guides when to use it vs siblings. It also notes the tool is free with no account needed. However, it does not explicitly state when not to use it or alternative tools for related tasks.

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 carries full burden. It discloses cost ($0.12/call), data sourcing (respects robots.txt, citations from corpus not invented), and limitations (names patterns it cannot assess). This goes well beyond the schema and provides critical behavioral context for an AI agent.

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

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

The description is compact (4-5 sentences) and front-loaded with the primary action. Each sentence adds distinct value: overview, output list, citation policy, limitation disclosure, cost. No redundant or filler 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's complexity (multiple output types, no output schema), the description provides a good overview of what is returned but lacks structural details (e.g., format, pagination). It does mention key behavioral aspects (cost, citation honesty). Slightly incomplete for a comprehensive tool, but sufficient for most use 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?

Schema coverage is 100%, and the description's parameter details (url, goal, html, jurisdiction) exactly match the schema descriptions. The description adds no new semantic information beyond what the schema already provides, so it meets the baseline but does not exceed it.

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

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

The description begins with a clear verb+resource: 'Audit a live page or raw HTML for conversion psychology.' It then enumerates specific outputs (cognitive load, dark patterns with regulation/evidence, trust-signal gaps, ranked findings), distinguishing it from sibling tools that focus on single aspects like psych_dark-pattern-detect or psych_cognitive-load.

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 comprehensive use by listing multiple analysis types, but it does not explicitly state when to use this tool vs. more specific siblings (e.g., 'for a full audit; use psych_dark-pattern-detect for only dark patterns'). No exclusions or alternatives are given, but the scope is clear enough for an agent to infer.

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 and discloses determinism, model-free reproducibility, respect for robots.txt, cost, and the inference from ambiguity aversion. It lacks details on error handling or output format but is largely 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 paragraph that front-loads the main purpose, then efficiently details signals, reasoning, and behavioral notes. Every sentence adds value with no waste.

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 that each gap is returned with an inference, but does not specify exact output structure. However, for a simple checklist tool, this is 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 coverage is 100% with descriptions for both parameters. The tool description adds value by noting robots.txt respect for url and precedence of html over url, providing behavioral context 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 tool checks which trust signals a page carries and which it omits, listing specific signals (pricing visibility, privacy and terms, contact routes, cancellation terms). This distinguishes it from sibling tools like psych_biases or psych_dark-pattern-detect, which address different psychological aspects.

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 use when assessing trust signals on a page through context, but does not explicitly state when not to use or provide alternatives. However, the distinct focus on trust signals among siblings provides clear context.

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

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

No annotations provided, so description carries full burden. It discloses data source (OpenStreetMap), cost per call ($0.000800), deduplication of OSM elements, and ambiguity flagging. However, it does not mention auth, rate limits, or error handling.

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 core action and output, then additional features. Every sentence adds value without redundancy.

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

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

No output schema, so description adequately explains output components (coordinates, address components, confidence, precision classification). Covers deduplication and ambiguity. Misses error cases and pagination, but overall sufficient for the tool's simplicity.

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 3 parameters with 67% description coverage. The description restates the purpose of the 'query' parameter but adds no new semantics. It does not explain 'limit' or 'country_codes' 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?

Description clearly states the tool converts a free-form address or place name into coordinates with normalized components, confidence score, and precision classification. It also mentions deduplication and ambiguity handling, making the purpose specific and distinct from sibling tools.

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 geocoding addresses and mentions cost and data source, but lacks explicit guidance on when to use vs. alternatives or when not to use. Sibling tools are in different domains, so the context is clear enough.

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

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

With no annotations, the description carries full burden. It adds valuable behavioral info: 'Free — this call costs nothing,' and lists the return fields. This is sufficient for a read-only catalog tool.

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

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

Two sentences total. The first sentence front-loads the purpose and output fields. The second adds cost and strategic advice. 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?

Despite no output schema, the description explicitly names the return fields (price, sourcing class, evidence grading, latency SLO, input schema). Combined with zero parameters, the description fully informs the agent.

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

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

The tool has zero parameters, so baseline is 4. The description adds no parameter info as none exist, but doesn't detract.

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 ('List') and names the resource ('Tollmint products') along with the specific fields returned. It clearly distinguishes from siblings like 'tollmint_quote' which likely handles quoting.

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 says 'Call it first to see what is available and what it costs,' providing clear when-to-use guidance. It does not explicitly list alternatives or when-not-to-use, but the context implies it's a discovery 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 carries full burden. It discloses that the call is free and the price is binding, but does not address authentication, rate limits, or side effects. The behavioral traits are partially covered but not comprehensively.

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, concise and front-loaded with the primary purpose. Every sentence adds value: first defines action, second clarifies cost and binding nature. No wasted words.

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

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

Given no output schema, the description should explain what the tool returns. It mentions 'exact price' and 'quoted price' but does not specify format or additional fields. For a simple tool this is adequate but not 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%, baseline is 3. The description does not add any parameter-specific information beyond what the schema already provides (e.g., input is described as 'the input you intend to send' in both places). No enrichment.

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

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

The description clearly states the tool's purpose: 'Get the exact price of a specific call before making it.' This specifies a verb (get), a resource (price of a call), and a context (before making the call), distinguishing it from siblings like tollmint_catalog which likely lists products.

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 ('before making it') and notes that it's free, but does not explicitly state when not to use or provide alternatives. The sibling list does not include another pricing tool, so the guidance is sufficient for context.

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

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

No annotations provided, so description carries full burden. It discloses fetching with robots.txt, citing sources with URLs, reporting dead rules, and not determining liability, giving clear behavioral expectations.

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

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

The description is thorough but slightly verbose. Each sentence adds value, but some detail (e.g., specific dead rules) could be more concisely stated without losing clarity.

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?

Complex tool with 5 parameters and many siblings, but no output schema. Description covers input options, return info (citations, dead rules), and limitations (no liability determination), making it complete for agent 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 covers all 5 parameters with descriptions, so baseline is 3. The description adds overall context (e.g., cost, rule count) but does not enhance parameter-level semantics beyond 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 checks marketing copy or live pages against 225 curated regulatory rules, covering specific areas like AI-disclosure, claims, subscriptions, etc. It distinguishes from more specific sibling tools (e.g., legal_claims) by being a comprehensive scan.

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

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

The description explains inputs (url, html, or text) and notes the tool does not determine liability. It implicitly provides context for when to use (compliance checks) but does not explicitly state when not to use or suggest alternative 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?

Discloses extraction method (link density), fallback behavior, what content is removed (navigation, banners, etc.), and reports retention stats. Also mentions honoring robots.txt and refusing private/auth pages. No annotations present, so description fully carries transparency burden.

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 well-organized sentences, front-loaded with core purpose. Each sentence adds unique value (purpose, detection method, restrictions/cost). Slightly long but efficient; 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?

Covers input parameters, output contents, extraction approach, restrictions, and pricing. Lacks return format details or error states, but given no output schema, the description provides adequate context for a content-extraction 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?

Adds context beyond schema: url's robots.txt compliance, max_words truncation reporting, include_links token reduction hint. Schema already provides descriptions for all 4 parameters, but description enriches usage semantics for each.

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 'Fetch a URL and return the main content as clean markdown' with specific verb and resource. It distinguishes from sibling tools (mostly psych/design analysis) by focusing on web content extraction and cleanup.

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 extracting clean content from web pages but does not explicitly state when to use or provide comparisons to alternatives. Mentions restrictions (robots.txt, private addresses) but lacks explicit guidance on context or exclusions.

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