AMZScout Skill + MCP

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

Annotations already provide readOnlyHint, and the description does not contradict that. It adds meaningful behavioral context beyond the schema: the tool pulls live data and performs analysis internally, and it mandates an exact output contract (verbatim copying of any 'Account notice:' paragraph). This is valuable but not exhaustive—e.g., failure modes or error handling are not disclosed.

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

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

The description is front-loaded with purpose and usage guidance, then proceeds to the output contract. The mandatory-notice section is lengthy but carries critical operational weight. Every sentence earns its place; only minor redundancy in the two examples keeps it from a 5.

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 broad agent-style tool with no output schema, the description covers its main inputs, scope, behavioral boundaries, and a custom output rule. It doesn't mention auth requirements or explicit failure scenarios, but those are largely covered by annotations and the surrounding tool context. Overall, an agent can use it safely and 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 100%, with both params already described. The description enriches the `message` parameter by showing three concrete natural-language examples and by clarifying no sub-tool selection is required—an implicit hint about what kind of input is expected. It doesn't add detail about `history` semantics, but the schema already covers 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 opens with a crisp role definition: an Amazon research assistant that answers natural-language questions and internally runs 'the right analyses.' It explicitly contrasts itself with granular sibling tools by stating that no sub-tool selection is needed, making the tool's unique purpose unmistakable.

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?

Usage guidance is explicit: 'Best for a hands-off answer' is directly followed by the alternative, 'the granular amzscout_* tools when step-by-step orchestration is preferred.' This gives the agent a clear decision rule for choosing this agent over its siblings.

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

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

Annotations declare readOnlyHint=true, and the description reinforces this with 'Pure data fetch (no AI analysis)'. It adds behavioral context beyond annotations: the output contract for 'Account notice:' paragraphs, and the instruction to reason over returned data. It doesn't describe rate limits or auth, but the read-only nature is well covered.

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 dense but well-organized: it front-loads the core purpose, then usage guidance, then the output contract. Every sentence earns its place, though the output contract is long and could be considered slightly verbose. Still, it's necessary for correct invocation.

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 (nested filters, multiple marketplaces, no output schema), the description covers the key behavioral contract (output handling) and usage context. It doesn't explain return value structure in detail, but the description explicitly says to reason over the returned data, which is sufficient for an agent. The lack of an output schema is partially compensated by the description's guidance on what to look for.

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

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

Schema description coverage is 100%, so the schema already documents all parameters. The description adds interpretive context for the returned aggregates (e.g., revenueTop5SharePercent) but doesn't add much parameter-level meaning beyond what the schema provides. 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 states a specific verb and resource ('Market snapshot for an Amazon niche/keyword — top products by revenue plus computed aggregates'), and explicitly distinguishes itself from AI analysis ('Pure data fetch (no AI analysis)'). It also names sibling tools like amzscout_compare_niches and amzscout_analyze_product implicitly by focusing on a single niche snapshot, making its purpose clear.

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 how-to-use guidance: 'judge niche attractiveness — demand concentration... price bands... review counts as entry moats... standout products'. It also includes a mandatory output contract for handling 'Account notice:' paragraphs, which is a clear when-to-use/behavioral instruction. It doesn't explicitly name alternatives, but the usage context is strong enough to guide an agent.

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 annotations already declare readOnlyHint=true, and the description reinforces this with 'Pure data fetch (no AI analysis)'. It adds important behavioral detail beyond annotations: the mandatory 'Output contract' for the account notice, including the verbatim copy requirement, and the variability of history data ('when available').

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, then the analytical workflow, then the mandatory output contract. The output contract is verbose but functionally necessary. It could be slightly tightened, but no sentence is pure filler.

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

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

With no output schema, the description needs to convey what the tool returns, and it does: price, sales/revenue, reviews, rating, listing quality, sellers, and history when available. It also addresses an edge case (account-only notice) and explains how to use the returned data, which is strong for a data-fetch tool.

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

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

The input schema has 100% description coverage, so the parameters are already well documented. The description adds little beyond identifying the resource as a single product by ASIN; it doesn't enrich the marketplace or ASN details beyond what the schema already states.

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 names the exact resource and action: fetch full raw product data for a single ASIN. It also distinguishes itself from analysis tools by emphasizing 'Pure data fetch (no AI analysis)' and from set/niche tools by saying 'single product'.

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 gives a clear usage context: audit the product like a sourcing analyst and conclude GO/NO-GO. It does not explicitly name sibling alternatives or state 'use this when you need one product, not a set/niche,' but the single-ASIN scope and pure-data framing make the intended use reasonably 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?

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds valuable behavioral context: it is a 'pure data fetch (no AI analysis)', meaning the agent must reason over the data itself. It also discloses the mandatory output contract for 'Account notice:' paragraphs, which is a critical behavioral trait not visible in annotations or schema. The only minor gap is that it doesn't describe the exact return format beyond 'product rows plus computed aggregates', but the output contract and pure-fetch disclosure are strong additions.

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 dense but well-organized: purpose, differentiation, usage pattern, and output contract are each addressed in distinct sentences. The output contract section is verbose but earns its place because it mandates critical reply behavior. Slight redundancy in the output contract ('Never omit, shorten, or paraphrase it' after already saying 'copied verbatim') is minor. Front-loading is good — the core purpose and differentiation come first.

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

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

For a read-only data-fetch tool with 100% schema coverage and no output schema, the description covers the essential context: what the tool returns, how to use it, and the mandatory output contract. The only missing piece is a more precise description of the response structure (e.g., field names, pagination), but since there is no output schema and the tool is a pure data fetch, the description is largely complete. The output contract is a critical addition that makes the tool safely callable.

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

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

Schema description coverage is 100%, so the schema already documents both parameters (asins array with min/max and auto-correction, marketplace enum with default). The description adds the '2–100 ASINs' constraint and the 'mini-market' framing, but doesn't add meaning beyond what the schema provides. Baseline 3 is appropriate when the schema does the heavy lifting.

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 verb ('analyze'/'fetch'), a precise resource ('explicit set of 2–100 ASINs'), and the exact scope ('product rows plus computed aggregates'). It also distinguishes itself from the keyword-based sibling (analyzeNiche) by naming the alternative and the condition that selects it. An agent can tell this apart from amzscout_analyze_product and amzscout_analyze_niche without opening the schema.

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 when to use this tool ('explicit set of ASINs') and when not to ('To discover products from a keyword instead, analyzeNiche is the equivalent'). It also provides a concrete usage pattern ('treat the set as a mini-market — segment products into groups, spot where demand concentrates, flag outliers...'). This is clear, actionable guidance with an explicit alternative.

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 goes beyond the readOnlyHint annotation by explicitly stating 'Pure data fetch (no AI analysis)' — reinforcing the read-only nature and setting agent expectations. It also discloses the special 'Account notice' output handling, which is a behavioral rule not captured in annotations. No contradictions with annotation.

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 long but each section earns its place: the purpose is front-loaded, usage guidance follows, and the output contract is crucial for correct execution. It is structured with clear separations (use cases, contract). Slightly verbose but not wasteful.

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 compensates by detailing the kinds of data returned (per-niche product sets, price/sales/revenue distributions, concentration, brand spread). It also covers the mandatory output contract and interpretation guidance, making it complete for an agent to invoke and handle 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 100% and the description adds no extra parameter-specific meaning beyond what the schema provides. The description focuses on output interpretation rather than parameter semantics, so it neither adds nor detracts; 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 states a specific verb and resource ('head-to-head data for 2–5 Amazon niches / category keywords') and distinguishes itself from the sibling 'compareProducts' by noting that tool is for ASINs. It clearly communicates the tool's role as a raw data fetch, not analysis, making it easy to tell apart from analysis tools like analyze_niche.

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 explains when to use the tool and how to interpret results ('weigh demand against competition... give a verdict'). Names the alternative 'compareProducts' for ASINs, providing a clear routing decision. Also includes a mandatory output contract that dictates exact reply behavior, which is critical usage instruction.

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

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

Annotations declare readOnlyHint=true, and the description adds 'Pure data fetch (no AI analysis)' along with conditional 'history when available' and the mandatory Account notice output contract. These go beyond the annotation and tell the agent what response quirks to expect and how to handle them.

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 then gives a focused how-to and output contract; every sentence carries functional information. Slightly verbose due to the detailed contract and usage steps, but no filler.

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

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

Given only two well-documented parameters and no output schema, the description covers the data fields, the no-analysis expectation, the single-ASIN alternative, and the mandatory output handling. Nothing essential for calling this tool correctly is missing.

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%, with asins and marketplace already documented including the 0/O auto-correction rule. The description does not add parameter-level meaning beyond that, so the baseline of 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 first sentence states a specific action and resource: side-by-side raw data for 2–5 Amazon products by ASIN, with a concrete field list (price, sales/revenue, reviews, listing quality, history). It also differentiates from siblings by explicitly saying it is a pure data fetch with no AI analysis and pointing to analyzeProduct for single ASINs.

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?

Gives an explicit selection rule: use this tool when you need raw side-by-side data for 2–5 ASINs and will do the comparison yourself, and names analyzeProduct as the equivalent for a single ASIN. The no-AI-analysis note plus the how-to block reinforce when this tool 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?

The description states it returns a welcome message and example questions, and instructs to relay output verbatim. While the readOnly annotation is present, the description adds context about the output and handling, which is useful for the 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 concise enough, though it repeats the trigger examples. It is not overly verbose and is structured in a single clear sentence, which is 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 the simple nature (no params, no output schema), the description fully covers what the tool does, when to use it, and how to handle its output. No additional information 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?

The tool has zero parameters, so the baseline is 4. The description does not need to explain any parameter details, and the empty schema is fully covered.

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 a welcome message and example questions, and explicitly distinguishes itself from other AMZScout tools by its demo/greeting purpose. The name 'amzscout_demo' is reinforced by the description, making its function unambiguous.

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

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

Provides explicit usage triggers: call at the very start of conversation, on greetings, or when user says specific phrases like 'Ask AMZScout', 'demo', 'begin', etc. This leaves no ambiguity about when to invoke the 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?

The description goes far beyond the readOnlyHint by disclosing the cached AI pre-validation, the keyword-search filtering mechanism, the no-match fallback that returns appearing brands, and the mandatory account-notice output contract. This is exactly the behavioral context an agent needs to invoke and respond correctly.

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 core action is front-loaded, behavioral caveats follow immediately, and the lengthy output contract earns its place because verbatim reproduction is mandatory. There is no filler or repetition.

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?

There is no output schema, so the description carries the burden of explaining what happens on success, on no-match, and when an account notice is present. It covers all three, plus how the results should be analyzed, leaving no critical gap for invocation or response 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 description coverage is high (80%), with descriptions/enums for brand, count, filters, and marketplace. The description does not add parameter-level detail beyond noting the brand-matching behavior, so the 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 opens with a specific action and resource: 'List products under a specific Amazon brand.' It clarifies that results are keyword-search rows matched on the brand field, but it never distinguishes itself from the sibling search_products tool, so it stops short of full sibling differentiation.

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

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

The 'How to use' paragraph gives useful guidance for interpreting results, and the pipeline description implies a brand-scoped discovery use case. However, it does not explicitly state when to choose this over amzscout_search_products or when not to use it; the usage guidance is about analysis, not tool 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?

Beyond the readOnlyHint annotation, the description discloses that this is a pure data fetch with no AI analysis, explains the difference in row content for ASIN vs keyword scope, and mandates the output contract for 'Account notice:' paragraphs. These are significant behavioral details not covered by annotations.

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 well-structured: purpose first, then data fields, then usage advice, then the mandatory output contract. Every sentence serves a purpose, though the output contract could be considered verbose. The structure is logical and front-loaded with the core functionality.

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 three optional parameters and no output schema, the description is remarkably complete. It explains the data returned, how to interpret it, and imposes a clear output contract. Nothing an agent needs to call it correctly or process the response is missing.

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

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

The schema already documents each parameter with 100% coverage, so the baseline is 3. The description adds value by clarifying the mutually exclusive scopes (asin vs keyword) and explaining that rows not ranking are marked, which is not in the schema. It does not elaborate on marketplace defaults, but the schema covers that.

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 verb ('get') and resource ('keywords') and immediately clarifies two scopes (ASIN-scope vs keyword-scope), which distinguishes it from sibling analysis tools. It enumerates the data fields returned, making its purpose unmistakable.

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 on when to use the tool (for keyword/SEO/PPC data) and how to apply the results for targeting and niche demand. However, it does not explicitly contrast with sibling tools like amzscout_analyze_niche or amzscout_analyze_product, so the exclusion criteria are implied rather than 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?

Annotations already mark readOnlyHint=true, and the description adds a critical behavioral contract: if the output starts with an 'Account notice:' paragraph, the reply must copy it verbatim. This is useful, non-obvious behavior beyond what annotations convey.

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 purpose and usage are stated up front, and the output contract is lengthy but necessary for correct behavior. The phrasing is a bit repetitive between the first sentence and the 'Use for...' sentence, but every essential instruction is present.

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

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

For a simple one-parameter, read-only tool, the description covers the key context: what the tool returns, when to use it, and a mandatory output handling rule. There is no output schema, so the output contract partially compensates, but the catalog contents and link behavior are not detailed.

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% and the one parameter, useCase, is already well documented with an example. The description adds little beyond restating the use-case concept, so the 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 clearly states the tool returns the AMZScout/Sellerhook catalog for a given use-case and is meant for recommending the right tool. It is distinct from the analyze/search siblings in function, though it does not explicitly name a sibling to differentiate from.

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 to use it for 'which AMZScout tool should I use for X' questions, giving clear context. It does not mention when not to use it or point to alternatives, 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 readOnlyHint annotation is confirmed and, more importantly, the description discloses a critical non-obvious behavior: results may begin with an 'Account notice:' paragraph that must be copied verbatim into the reply. This is exactly the kind of behavioral context beyond annotations that agents need.

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 than average, but every sentence earns its place: purpose, return value, usage, and a mandatory output contract. It is front-loaded with the core purpose before the contract details.

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

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

For a read-only search tool with two well-documented parameters and no output schema, the description is complete: it states what is searched, what is returned, when to use it, and the one special output condition. An agent has enough to invoke it correctly.

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

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

The input schema already describes both parameters completely (query and topK with ranges/default). The description adds no extra meaning about how queries are interpreted or how topK affects results, so it does not need to compensate; 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 names a specific operation (TF-IDF search across the AMZScout knowledge base) and a concrete resource ('Amazon-seller tutorials, brand reference, glossary'), plus the return payload (title, source URL, text). Among siblings focused on product/niche analysis, this is clearly the knowledge-retrieval tool.

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

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

It explicitly states when to use the tool: 'Use this to ground answers in factual material.' It lacks explicit exclusions or named alternatives, but the phrase gives enough context for an agent to prefer it for knowledge-base grounding over sibling search/analysis 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?

Annotations already mark readOnlyHint=true, and the description reinforces it with 'Pure data fetch (no AI analysis)'. It adds a critical behavioral disclosure: the mandatory OUTPUT CONTRACT about the 'Account notice:' paragraph, including verbatim copying and the [View Plans] link. This goes beyond annotations and is essential for correct agent 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 longer than typical but every sentence earns its place: purpose, differentiation, usage guidance, and the critical output contract. The most important instruction (output contract) is clearly marked and placed at the end. Slight verbosity in the 'How to use' section could be trimmed, but overall it is well-structured and front-loaded with 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?

With no output schema, the description covers the return fields (price, sales, revenue, reviews, rating) and the mandatory output contract. It does not explicitly state that the result is a list of product objects, but the mention of 'rows' and 'top N products' implies that. For a read-only search tool with full schema coverage, this is nearly complete; minor gap is lack of mention of pagination or result count 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?

Schema description coverage is 100%, so the input schema fully documents all parameters (sort, count, query, filters, marketplace) with enums and defaults. The description adds only generic references to 'specific sort order or filters' without introducing new meaning beyond the schema, matching the baseline 3 for complete 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 states a specific verb ('Keyword search'), resource ('Amazon'), and return payload (top N products with price, sales, revenue, reviews, rating). It explicitly differentiates from sibling analyzeNiche by clarifying this is raw data fetch without AI analysis, so an agent can select it correctly.

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 states when to use: 'Best when you need raw product rows (specific sort order or filters)' and names the alternative analyzeNiche that returns computed aggregates. Also provides 'How to use' guidance on scanning rows for entry-opportunity signals, giving clear context for invocation.

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

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

Beyond the readOnlyHint annotation, the description adds critical behavioral details: it is free and doesn't consume tokens, and it specifies the mandatory output contract for handling 'Account notice:' paragraphs. These are non-obvious behaviors that materially affect how an agent should process the result, so the description fully carries the 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?

The description is well-structured: purpose first, then usage, then output contract. The output contract section is verbose but essential and unambiguous. No filler words; every sentence serves a functional role, so it earns high marks for conciseness despite moderate length.

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, read-only, parameter-free tool, the description covers everything an agent needs: what it does, when to call it, how to interpret its output, and special formatting requirements. The lack of an output schema is compensated by the explicit output contract instructions, making the tool 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?

With zero parameters, the schema provides no semantic content. The description doesn't need to explain parameters, but it does describe what the tool returns (balance figures) and how to report them, adding value beyond the empty schema. Baseline for 0 params is 4, and the description meets this without overreach.

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 identifies the tool as reporting the caller's AMZScout token balance (remaining, used, and limit), a specific resource and action. This is distinct from the sibling tools, which all perform analysis or search functions, leaving no ambiguity about the tool's 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?

It explicitly states when to use the tool: in response to token balance queries or when a call fails on quota. It also provides a concrete 'How to use' section with example user prompts, and clarifies the free nature (no token charge), which is a key usage consideration. No alternatives are needed since it's the only usage tool.

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