Orange Peel

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

With no annotations provided, the description carries the full burden. It discloses the tool's informational nature and the behavioral restriction of citing only allowed data, while also specifying attribution requirements. It does not explore side effects, but none are implied.

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

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

Two concise sentences communicate the tool's purpose, usage, and content. The key instruction 'Call this first' is prominently placed.

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 parameterless, informational tool, the description fully covers what the tool does, how to use it, and the agent's obligations. No output schema exists, but the content is self-contained and sufficient.

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 is empty, so there are no parameters to document. Baseline of 4 applies; no additional parameter information is needed.

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

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

The description clearly states that the tool provides information about Orange Peel, the data citeable, and attribution rules. It is distinguishable from sibling data-retrieval tools by its meta-purpose, though the verb is implied rather than explicit.

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 instruction 'Call this first' explicitly indicates when to use the tool, positioning it as a prerequisite for siblings. No exclusions or alternatives are mentioned, but the context is 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 the full transparency burden. It discloses that figures are 'documented/estimated and cited — never an appraisal,' which is an important behavioral caveat. It also specifies that the resale price is for 'pristine' condition, adding context about the estimate's scope. This goes beyond a simple purpose statement, though it does not detail request mechanics or data sources.

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, well-structured sentence that packs all essential information—what is returned, the geographic/currency scope (US), the condition (pristine), and the crucial caveat about citations and non-appraisal—without unnecessary repetition. Every clause 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?

For a simple two-parameter lookup with no output schema, the description adequately covers the core return values (retail, resale, premium) and the nature of the data. It could explicitly mention the currency format or the response structure, but given the tool's simplicity and available schema, the description is sufficiently complete for an agent 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 provides 100% coverage for both required parameters (model and size) with descriptive examples. The description does not add additional parameter-specific meaning, only contextualizing the overall price data. Since schema coverage is high, a 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's function: it returns the current cited US retail list price, estimated pristine secondary-market resale price, and the resale-over-retail premium for a Hermès bag. This specific verb+resource+output distinguishes it from sibling tools like get_market_median or get_price_history, which focus on aggregate or historical data.

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

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

The description clearly implies when to use this tool: when you need current retail and resale prices for a specific Hermès bag model and size. It does not explicitly name alternatives or exclusion criteria, but the context is clear enough for an agent to select it over broader price tools. However, it would benefit from explicitly noting that other tools cover different price aspects, so it gets a 4 rather than 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?

With no annotations, the description carries the full burden. It adds valuable behavioral context: the metric is 'community-reported', represents a 'median', and is 'position not probability' — clarifying what the number does and does not mean. This goes beyond a simple read hint.

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

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

Two concise sentences with no filler. The key term is front-loaded, and the definition is provided efficiently. The brief clarification about community-reported and position-not-probability earns its place.

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

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

The tool has no output schema, so the description should explain return values. It defines the metric but does not explicitly state the return format (e.g., number, ratio, percentage) or any caveats like data availability. It is minimally adequate for a simple getter.

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 city parameter is adequately described. The description adds minor context by indicating the benchmark is city-specific, but does not provide additional meaning beyond the schema.

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

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

The description clearly states the tool gets a community-reported pre-spend benchmark for a city, with a specific metric definition. It doesn't explicitly distinguish from siblings like get_market_median, but the unique concept of 'pre-spend ratio' is specific enough.

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

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

No explicit when-to-use guidance or alternative tool comparisons are provided. The description implies usage for checking pre-spend benchmarks per city, but does not explain when it should be preferred over related tools.

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

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

With no annotations provided, the description carries the full burden. It clearly discloses that the result is live, cross-site, based on current asking prices (not sold prices), and includes listing count and retrieval date. It does not mention potential errors or cache behavior, but for a read-only query tool this is adequate.

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

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

The description is concise, with two sentences containing no redundant words. It front-loads the core purpose and immediately specifies the key output fields and an important caveat ('never sold').

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 is simple with one parameter and no output schema, and the description explains what output to expect (median, n, date). It is complete enough for an agent to know what the tool returns and what data it aggregates, though it could mention currency or exact marketplace list.

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 provides a thorough description of the single parameter 'spec' with an example, achieving 100% coverage. The description adds no additional parameter-level semantics, so the baseline score 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 it returns a live cross-site median of current asking prices for a specified bag, with count and retrieval date. It distinguishes itself from siblings like get_bag_price and get_benchmark by emphasizing the median across marketplaces and clarifying 'asking prices only'.

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 clear usage: use when you need the current market median asking price for a bag spec across multiple resale sites. It does not explicitly name alternatives or exclusions, but the context is clear enough for correct selection among 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?

With no annotations provided, the description carries the burden of behavioral disclosure. It reveals that the series is 'LIVE weekly median-ASK' and that 'Archived (2015–2019 Internet-Archive) and cited SOLD anchors are partner-tier depth and are teased, not returned,' which is a significant limitation not visible in the schema. It lacks details on rate limits or errors, but the key access restriction is 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 two sentences long, front-loaded with the core output and scope, and includes a limitation clause without unnecessary elaboration. The term 'teased' is slightly jargon-y but acceptable; the structure is efficient and easy to parse.

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

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

The description covers the main purpose and a key access restriction, but it doesn't specify the return format or pagination behavior, and since there is no output schema, this information is missing. It also doesn't differentiate this tool from sibling price tools like get_market_median or get_price_increases, leaving some contextual gaps.

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% since both spec and timeframe have descriptions with enum values. The tool description adds contextual meaning about the data being weekly median-ASK but does not enrich the parameter semantics beyond what the schema already provides, 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 'LIVE weekly median-ASK series for a bag spec,' specifying the resource and scope with notable differentiation from archived/sold anchors. It distinguishes itself from siblings by mentioning 'median-ASK' vs. 'SOLD anchors' and depth tiers. A minor issue is the absence of an explicit verb like 'returns' or 'fetches,' but the intent is unambiguous.

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

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

The description implies this is the tool for live median-ASK price data and notes that archived/sold anchors are 'teased, not returned,' which suggests when not to use it for sold-price needs. However, it does not explicitly name alternative tools or provide clear when-to-use/not-to-use guidance, leaving usage mostly implied.

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

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

With no annotations, the description carries the burden of behavioral disclosure. It explains that the result is a 'dated record of verified past increases' with source and retrieved date, and explicitly denies being a forecast. This provides useful context about the nature and provenance of the data, though it doesn't detail the exact return format.

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

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

The description is two sentences, front-loaded with the core purpose, and every clause adds value. The second sentence explicitly clarifies a critical non-behavior (not a forecast), which efficiently prevents misuse without extra fluff.

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

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

For a single-parameter tool with no output schema, the description covers the essential expectations: what the data is (verified past increases), its structure (source + retrieved date), and what it is not (forecast). It could briefly mention the return format (e.g., list) but the wording 'dated record' implies this sufficiently.

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 has 100% coverage with an enum for brand and a clear description. The tool description merely restates the brand names, adding no new meaning beyond what the schema provides. Baseline 3 is appropriate since 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 clearly identifies the tool as a 'retail price-increase ledger' for Hermès or Chanel, with 'a dated record of verified past increases'. It uses specific verbs and resources, and the second sentence explicitly distinguishes it from a forecast, which helps differentiate it from siblings like get_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?

It states the tool is for past increases and 'never a forecast', implying this is not for predicting future hikes. It gives the context of the two brands but does not explicitly name alternative tools, leaving the agent to infer that other sibling tools might cover different data types.

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