ANIME INTELLIGENCE

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

Annotations already declare readOnly/openWorld/idempotent, and the description adds meaningful context: it is a paid pre-purchase screen ('Price: 0.02 USDC via x402'), payment happens only after the service resolves and ranks the product, and it flags bootleg risk/identity mismatches. No contradiction with the non-destructive readOnlyHint.

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 verbose but well-structured with labeled sections (WHEN TO USE, WHY PAY, BUYER OUTCOME) and the core purpose is front-loaded. Some redundancy exists—common agent queries overlap with schema examples—but the organization makes the length navigable and useful.

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 paid specialist tool with 7 parameters and an output schema, the description covers invocation triggers, pricing, exclusions, and sibling routing. The presence of an output schema means return values do not need to be spelled out, and nothing needed to select or call 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 high (86%), and parameter-level descriptions in the schema already explain query types, listing_url, listing_title, and buyer_country. The prose description adds little beyond re-stating that broad multilingual queries are auto-ranked before payment, which is already in the query schema, so a 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 opening line states a specific function—'Pre-purchase counterfeit and listing-risk screening for Japanese anime collectibles'—with clear scope and outcome. It is further differentiated from siblings by naming Full Intelligence as the fallback for broader tasks and by listing bootleg/counterfeit triggers, so an agent can identify when this specialist tool applies.

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

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

Explicit WHEN TO USE conditions are given ('unusually cheap, seller title vague, official references missing...') and a clear exclusion set ('Do not use for anime news, plot, streaming or character biography'). It also tells the agent to prefer Full Intelligence when the single signal does not fully answer the task, making routing unambiguous.

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 indicate a safe read-only, idempotent operation, and the description adds useful extra context: a 0.02 USDC x402 payment, pre-payment canonical product resolution, and the fact that it produces a decision rather than executing a purchase. No contradiction with 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 heavily redundant: WHEN TO USE and WHY PAY cover similar ground, and Selection triggers largely duplicates Common agent queries. While the headings make it skimmable, several sentences repeat the same point and the description is longer than necessary.

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 output schema, input schema, and annotations, the description covers the key decision context an agent needs: when to pay, what decision outcome to expect, example queries, product resolution behavior, and when to defer to Full Intelligence. Nothing critical for tool selection 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 86% and the query parameter already documents product names, categories, JAN/EAN-13, model numbers, multilingual input, and auto-ranking before x402. The description largely restates this information, so it adds little beyond the schema's already-rich parameter documentation.

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 decision output — BUY, WAIT, WATCH, or AVOID — from Japanese collectible data, and explicitly contrasts itself with raw-data reporting and Full Intelligence. This makes it clearly distinguishable from its sibling specialist 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 includes an explicit WHEN TO USE section, example trigger phrases and queries, a clear exclusion ('Do not use for anime news, plot, streaming or character biography'), and names Full Intelligence as the alternative when this single signal is insufficient.

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, openWorldHint, idempotentHint, and destructiveHint, so the bar is lower. The description adds useful behavioral context: it resolves and ranks the canonical product before payment, accepts broad multilingual queries, and rejects mismatched editions. It does not disclose failure modes or payment side effects, but the added context goes beyond the 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 well-structured with WHEN TO USE, WHY PAY, BUYER OUTCOME, and selection triggers, and it front-loads the core purpose. However, it is considerably longer than needed and contains redundancy: the WHY PAY and BUYER OUTCOME sections repeat the identity-mismatch and valuation points already made in the opening paragraph.

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

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

For a complex, paid, identity-matched lookup with an output schema present, the description is complete: it covers purpose, invocation style, query language flexibility, exclusions, alternatives, pricing, and supported marketplaces. An agent has enough information to decide when to call it and what to expect.

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

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

Schema description coverage is 86%, so the schema carries most parameter documentation; baseline is 3. The description adds meaningful semantic context for query and id: query can be broad and is auto-ranked before x402, while id is for deterministic exact-product calls. This helps an agent choose the right calling mode beyond the raw schema.

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

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

The description names a specific verb and resource: identity-matched market intelligence for Japanese anime collectibles, returning low/median/high asking prices, offer count, freshness, and best matched listing. It also differentiates itself from generic marketplace search by emphasizing rejection of wrong editions and name collisions, so an agent can distinguish it from siblings like listing_match or price_history.

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 explicit when-to-use conditions ('when an agent needs current value, resale context or matched asking prices'), explicit not-to-use conditions ('Do not use for anime news, plot, streaming or character biography'), and names the preferred alternative when the signal is insufficient ('otherwise prefer Full Intelligence'). This is strong routing guidance.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, so the safety profile is covered. The description adds meaningful behavioral context beyond that: the 0.01 USDC x402 cost, the fact that broad multilingual queries are auto-resolved and ranked to a canonical product before payment, and the warning about avoiding a 'false rarity premium.' This goes well beyond the structured 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 long but carefully structured with labeled sections: WHEN TO USE, WHY PAY, BUYER OUTCOME, Price, Selection triggers, Common agent queries, and exclusion rules. It is front-loaded with the core purpose. Some redundancy exists between selection triggers and common queries, but the structure makes the length digestible and useful.

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, seven parameters, and an output schema, the description covers everything needed for correct invocation: purpose, payment, canonical product resolution, alternatives, exclusions, and sample queries. The output schema handles return-value documentation, so the description does not need to explain that separately. Nothing critical 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 86%, well above the 80% threshold, so the schema already documents most parameters. The description reinforces that queries can be broad and are auto-ranked, but most per-parameter meaning lives in the schema. Baseline 3 is appropriate because the description adds purpose context rather than new parameter-level semantics.

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

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

The description opens with a specific verb and resource: 'Estimate scarcity and rerelease/replenishment risk for the exact Japanese collectible, not just the franchise.' It clearly differentiates from sibling tools by emphasizing exact-product analysis rather than franchise-level data and by naming Full Intelligence as the broader alternative. This lets an agent understand the tool's unique role without needing to inspect other definitions.

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 provides 'WHEN TO USE', 'WHY PAY', selection triggers, common agent queries, and a direct routing rule: 'Use this specialist tool when this single signal fully answers the task; otherwise prefer Full Intelligence.' It also states what the tool is not for ('anime news, plot, streaming or character biography questions'). This is exemplary usage guidance with both positive and negative conditions.

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 readOnly/openWorld/idempotent, so the description correctly adds non-obvious behavior: the payment requirement ('Price: 0.03 USDC via x402'), the fact that the service resolves and ranks the canonical product before payment, and the identity-matching guarantee for seller offers. No contradiction with 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 front-loaded with the main action and organized into scannable sections (WHEN TO USE, WHY PAY, BUYER OUTCOME, Price, triggers, examples). There is some redundancy between 'WHY PAY' and 'WHEN TO USE,' but overall every section helps an agent decide quickly.

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 an output schema present, the description does not need to explain return values. It covers purpose, when to defer to Full Intelligence, exclusions, payment, trigger examples, and query flexibility, which is enough for an agent to select and call this tool correctly in 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 86%, and the input schema already explains query, id, lang, buyer_country, and the other parameters. The description mostly restates that broad multilingual queries are allowed, which is already in the schema. It adds little parameter-level meaning beyond what the schema provides, so the 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 first sentence uses the specific verb 'return' with a precise resource: 'the best current purchase route for an exact Japanese anime collectible.' It names the comparison dimensions (seller, price, availability, marketplace, freshness) and contrasts with 'a generic marketplace search page,' so an agent can clearly distinguish it 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 contains a dedicated WHEN TO USE section and an explicit selection rule: 'Use this specialist tool when this single signal fully answers the task; otherwise prefer Full Intelligence.' It also gives negative cases ('Do not use for anime news, plot, streaming or character biography questions') and lists trigger phrases, giving strong routing guidance.

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

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

Annotations already cover readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is clear. The description adds valuable extra behavior beyond annotations: it is a paid call at '0.05 USDC via x402,' it auto-resolves and ranks the canonical product before payment for broad queries, and it returns a decision rather than 'another list of links.'

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 a clear first sentence and uses helpful headings, but it is overly verbose and repetitive. 'WHY PAY' and 'BUYER OUTCOME' restate the one-call/replaces-multiple-searches point, and the 0.05 USDC pricing appears multiple times, so not every sentence earns its place.

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

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

Given that the tool has 7 parameters, no required parameters, an output schema, and a paid execution model, the description covers the essential operational context: pricing, payment routing, when to use it, exclusions, example queries, and destination-aware landed cost. It does not enumerate the specialized sibling tools for single-signal cases, but the output schema and annotations fill most of the remaining 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 86%, so the input schema already documents most parameters. The description adds general behavioral context, such as broad multilingual queries being auto-ranked before payment and the id being a canonical UUID for deterministic calls, but it does not provide significant per-parameter semantics beyond what the schema already offers.

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 deliverable: 'end-to-end Japanese anime collectible purchase decision' that resolves the exact edition, returns market intelligence, and produces a BUY/WAIT/WATCH/AVOID recommendation with the best purchase route. It also differentiates itself from the specialized siblings by positioning itself as the aggregate call for requests needing two or more of identity, value, rarity, authenticity, timing, and routing.

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 contains an explicit WHEN TO USE section, calls itself the 'default high-value call,' and gives a concrete selection rule: prefer this tool when the request needs two or more of identity, value, rarity, rerelease risk, authenticity, timing, or seller routing. It also provides exclusions: 'Do not use for anime news, plot, streaming or character biography questions.'

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 readOnly/openWorld/idempotent/non-destructive, and the description adds substantial context on top: pricing (0.005 USDC via x402), the pre-payment ranking behavior, that it 'return[s] confidence and alternatives' and 'expose[s] missing prior/social context instead of guessing'. This goes well beyond the structured hints and is consistent with them — no contradiction.

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 roughly 300+ words with substantial redundancy: the 'WHY PAY' and 'BUYER OUTCOME' sections restate the opening paragraph, and the 'Selection triggers' list overlaps with the 'Common agent queries'. Key info is front-loaded, but many sentences do not earn their place, making this over-specified for an MCP definition.

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 7-parameter paid tool with an output schema, the description covers usage boundaries, payment flow, output behavior (canonical product, confidence, alternatives), multilingual scope, and sibling routing. The output schema relieves it of explaining return shapes. The only shortfall is verbosity, not missing substance — nothing an agent needs to call it correctly is absent.

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

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

Schema coverage is 86%, so the schema already documents all 7 parameters in detail. The description reinforces the multilingual and vagueness-handling semantics of the query param and notes the buyer-country/landed-cost tie, but it does not add syntax or format details beyond what the schema provides. Baseline 3 is appropriate when the schema carries the load.

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 verb-resource pair — 'multilingual vague-to-canonical shopping intelligence for physical anime collectibles' — and explicitly distances itself from the sibling full_intelligence ('otherwise prefer Full Intelligence') and from news/plot/streaming questions. An agent can tell exactly what this tool does 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?

A dedicated WHEN TO USE section lists concrete trigger phrases and example queries, and the description gives an explicit exclusion ('Do not use for anime news, plot, streaming or character biography questions') plus a routing rule ('Use this specialist tool when this single signal fully answers the task; otherwise prefer Full Intelligence'). Usage boundaries are fully specified.

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, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context beyond that: it states the tool 'refusing to invent unavailable duty, tax or brokerage amounts' and surfaces uncertainty explicitly. It also discloses the payment requirement (0.02 USDC via x402), which is a critical behavioral trait for an agent. No contradictions with 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 long but well-structured with clear headers (WHEN TO USE, WHY PAY, BUYER OUTCOME, Price, Selection triggers, Common queries). It front-loads the core purpose and then provides practical trigger examples. Some sections like 'WHY PAY' could be trimmed, but overall it is organized and each part adds useful context for an agent. It earns a 4 rather than a 5 due to slight verbosity.

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

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

For a paid, specialist tool with 7 parameters and an output schema, the description covers all necessary context: when to use it, what it returns (known totals with surfaced uncertainty), limitations (refuses to invent amounts), payment details, and examples. It explicitly contrasts with Full Intelligence and lists do-not-use cases. The output schema is present, so return format doesn't need to be in the description. Nothing essential 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 86%, so most parameters are already documented. The description adds meaningful context for key parameters: it explains that 'query' can be a broad multilingual description and is auto-ranked, and that 'buyer_country' drives country-aware routing and uncertainty. It also clarifies the 'id' parameter for deterministic calls. This goes beyond the schema and compensates for the few undocumented parameters, though not perfectly, hence a 4.

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

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

The description states a specific verb and resource: 'Destination-aware purchase cost for Japanese anime collectibles.' It clearly distinguishes itself from siblings by explicitly naming Full Intelligence as the alternative when a single signal doesn't fully answer the task, and it lists selection triggers that map to its purpose. This is far from a tautology and leaves no doubt about what the tool does.

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

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

The description includes a dedicated 'WHEN TO USE' section, states 'Use this specialist tool when this single signal fully answers the task; otherwise prefer Full Intelligence,' and lists 'Selection triggers' and 'Common agent queries.' It also explicitly says 'Do not use for anime news, plot, streaming or character biography questions,' giving clear exclusions. This is exemplary usage guidance.

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

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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds meaningful behavioral context: it costs 0.01 USDC via x402, auto-ranks canonical product before payment, and falls back to returning the strongest observed matched listings when no URL/title is supplied. This goes beyond the annotations without contradicting 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 uses labeled sections (WHEN TO USE, WHY PAY, BUYER OUTCOME, selection triggers) for scannability. It is somewhat verbose and repeats the purchase context across sections, but each section still adds routing or behavioral 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 tool's complexity, the description covers input modes, payment expectation, fallback behavior, exclusions, and sibling differentiation. With an output schema present, it does not need to explain return values; the agent has everything needed to decide and invoke 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 86%, so the baseline is 3. The description adds value by explaining that a listing URL or title may be supplied and that otherwise the service returns observed matches, and by clarifying that broad multilingual shopping queries are accepted and auto-ranked. This supplements the already-rich schema descriptions without duplicating them.

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 verb and resource: 'Verify whether a seller listing matches the exact Japanese anime collectible, edition or variant.' It clearly signals the tool's niche—listing-to-canonical match verification—and differentiates it from sibling tools like identify_anime_product and full_intelligence by focusing on wrong-version and name-collision risk.

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 'Use immediately before purchase' and gives the selection triggers: same product, same edition, does this listing match, correct version, wrong version. It also states exclusions ('Do not use for anime news, plot, streaming or character biography questions') and names the alternative ('otherwise prefer Full Intelligence'), leaving no ambiguity about when to invoke 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?

Annotations cover read-only, open-world, idempotent, and non-destructive traits, so the bar is lower. The description adds valuable context: it clarifies this is asking-price history, not completed-sale history; discloses a 0.02 USDC payment via x402; and explains that broad queries are auto-ranked and canonical product resolved before payment. This goes beyond the annotation profile and helps the agent anticipate cost and processing.

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 divided into clear sections and front-loads the core purpose, which is good. However, it is quite verbose with marketing-like blocks like 'WHY PAY' and 'BUYER OUTCOME' that could be trimmed. The selection triggers and common queries add length without substantially improving clarity for an agent that already understands the use case.

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 (7 params, output schema, payment, multilingual queries), the description covers all essential aspects: what it returns, when to use it, exclusions, payment, and query handling. The presence of an output schema means return values need no explanation. The only minor gap is that it does not describe the exact format of the response, but that is covered by the output schema.

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

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

Schema description coverage is 86%, high, so the schema already documents all parameters. The description provides example queries and explains the query parameter's flexible input (product name, franchise, JAN/EAN, etc.) but does not add meaning beyond what the schema already gives. 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 stores asking-price history for a specific Japanese anime collectible and returns 7/30/90/180-day ranges, medians, percentile, and trend. It distinguishes itself from sibling full_intelligence by specifying it should be used when this single signal fully answers the task, and explicitly excludes non-price queries like news or character biographies.

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' with concrete conditions (before BUY/WAIT, when needing historical context) and 'WHY PAY' rationale. It also names the alternative full_intelligence and states when to prefer it, plus gives selection triggers and common example queries. Exclusion cases (anime news, plot, etc.) are clearly listed.

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?

Even with readOnly/openWorld/idempotent annotations, the description adds valuable behavioral context: it explicitly says unknown deadlines are returned as unknown rather than inferred from release dates, that release dates are kept separate from order cutoffs, that timing is never fabricated, and that payment is 0.01 USDC via x402. These details go well beyond the 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 longer than average but well-structured with labeled sections, front-loaded purpose, and practical query examples. Some redundancy exists between 'WHY PAY' and the later price line, but the structure aids an agent in quickly extracting when and why to call the tool.

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

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

Given an output schema exists and the description covers selection triggers, exclusion cases, payment, unknown-deadline behavior, and alternatives, nothing essential is missing for an agent deciding whether and how to invoke this tool. It even addresses multilingual shopping queries and payment ordering.

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 at 86%, so the schema already documents most parameters, including query, id, lang, and buyer_country. The tool description mostly repeats query-level behavior already present in the schema, such as allowing broad shopping queries and auto-ranking before x402. It adds little new meaning per-parameter beyond what the input schema 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 opens with a specific verb+resource: 'Purchase-window intelligence for Japanese anime collectibles' and explicitly enumerates the kinds of deadlines covered (preorder, lottery, reservation, sales). It differentiates itself from siblings by stating it is a 'specialist tool' that answers a single signal and directing agents to prefer Full Intelligence otherwise.

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 contains an explicit 'WHEN TO USE' section listing concrete trigger scenarios, a 'WHY PAY' rationale, and a clear exclusion: 'Do not use for anime news, plot, streaming or character biography questions.' It also names the alternative (Full Intelligence) and gives the condition for choosing this tool over 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?

The annotations already cover read-only, open-world, idempotent, and non-destructive behavior, so the description does not need to restate those. It adds useful context beyond annotations: the tool is free, returns candidate options rather than final answers, and has a deliberate boundary where paid-scope questions must be routed elsewhere. No contradiction with annotations exists.

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 and front-loaded, starting with the core value proposition ('FREE candidate discovery') before moving to usage context and exclusions. Every clause contributes decision-relevant information with no filler or repetition of schema 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 discovery tool with a rich output schema and comprehensive safety annotations, the description covers the essential facts: free access, when to use it, multilingual/vague query handling, and the boundary to paid specialists. Nothing needed for correct invocation or routing 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 query thoroughly with examples and a rich description, but the lang parameter only has an enum with no explanation. The description mentions 'multilingual queries,' which hints at language handling, but it never explains when or how to set lang. With 50% schema coverage and no explicit language-parameter guidance, the description only partially compensates.

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 'FREE candidate discovery for physical Japanese anime collectibles,' naming a specific action, object type, and cost model. It further clarifies scope by stating it handles vague and multilingual queries and explicitly positions itself as a pre-purchase discovery step rather than a final valuation 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: when the user wants options or when the agent needs to inspect alternatives before paying. It also gives clear exclusions, telling the agent not to stop here for value, rarity, authenticity, BUY/WAIT, or purchase-route queries and to select the matching paid specialist tool or Full Intelligence instead.

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