Carat Hunter

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds that the return includes a 'current price range', hinting at live/pricing data, but says nothing about auth, rate limits, or whether results are cached. With annotations doing the safety work, this is adequate but not rich.

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

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

A single front-loaded sentence with the resource, action, and id provenance. No filler; 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?

No output schema exists, but the description compensates by summarizing the return (details and price range). For a one-parameter read tool, this covers what an agent needs; only explicit sibling routing 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 description coverage is 0%, so the description carries the burden for the single `id` parameter. It does this well by naming the id system (Carat Hunter id) and its two valid sources, which the bare integer schema cannot convey.

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 gives a specific verb (retrieve details and current price range) and a precisely scoped resource (one diamond, by Carat Hunter id). It implicitly separates itself from search_diamonds by noting the id originates there, but does not explicitly state the contrasting case.

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 is implied: call this once you have a Carat Hunter id from search_diamonds or a carathunter.com URL. There is no explicit when-to-use vs when-not guidance against the other siblings (price_check, lookup_certificate, market_overview).

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 openWorldHint=false, and the description does not contradict them. It adds useful behavioral detail by explaining what the tool reports: retailer listings, count, and price range, which goes beyond a bare 'look up certificate' statement.

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

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

Two sentences with no filler. The action and identifier are front-loaded, followed by output summary and a practical use case. Every sentence contributes.

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, read-only lookup tool with no output schema, the description adequately covers the input, the useful output, and when to use it. It could be slightly stronger with an explicit alternative reference, but nothing critical is missing for correct invocation.

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

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

Schema coverage is 0%, so the description must clarify the parameter. It does so by defining certificate_number as a grading report number and naming accepted labs (GIA, IGI, HRD, GCAL), adding meaning beyond the schema's bare type and length constraints.

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

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

The description states a specific action ('Find a diamond') and a precise resource/identifier ('grading report number'), listing accepted labs (GIA, IGI, HRD, GCAL). It clearly differentiates from siblings by emphasizing exact-stone lookup rather than broad search or market overview.

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 use case: checking whether a quoted price is fair for a specific certificate number. It does not explicitly name alternatives or exclusion conditions, but the exact-stone framing implies when this tool is appropriate versus broader search 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?

readOnlyHint already establishes a read-only operation, and the description adds that the data is sourced from the latest weekly market report, implying a periodic snapshot rather than a live query. No destructive side effects, auth, or rate-limit concerns are relevant for a zero-argument read-only tool.

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

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

One sentence, front-loaded with the key value ('how many diamonds and retailers'), and 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?

For a zero-parameter read-only tool, the description fully conveys what the agent should expect: aggregate counts from a weekly report. No output schema exists, but the expected output shape is simple and sufficiently described.

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

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

There are no parameters and the schema is fully self-explanatory, so the baseline is 4. The description accurately reflects that the tool provides aggregate counts without needing any inputs.

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

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

States a specific outcome: report the number of diamonds and retailers Carat Hunter tracks. It differentiates itself from item-level siblings like get_diamond, search_diamonds, and price_check by offering a market-level summary.

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 intended use is implied by the market-overview context, but the description never explicitly says when to choose this over the sibling tools. It provides no exclusions such as 'use search_diamonds for individual stones' or 'use price_check for pricing.'

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 already covers safety, and the description adds useful behavioral context about the aggregation: median, middle-half range, and retailer-to-retailer variation. It does not mention data recency, currency, or exact return structure, but for a read-only aggregation tool the description provides solid behavioral insight beyond the 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 two sentences and front-loads the core purpose and output metrics. The carat-size list is slightly redundant with the schema enum but is a convenient summary. Overall it is concise and well-structured, with minimal waste.

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

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

The description provides a good high-level understanding of inputs and outputs, but with no output schema it leaves out return format details such as currency, units, and how the variation metric is represented. For an agent to fully interpret the result, more explicit output structure would be helpful.

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 has no parameter descriptions (0% coverage), but all five parameters are self-explanatory enums. The description identifies the spec dimensions and enumerates valid carat sizes, adding a little meaning beyond the schema, but it does not explain interpretation details like colour scale or origin values. This is adequate but not fully compensatory.

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 returns typical market prices for a diamond spec across all tracked retailers, and lists the output metrics (median, middle-half range, variation). It is clear enough to distinguish from specific-diamond lookups, but it does not explicitly differentiate itself from the sibling 'market_overview' or name alternative tools.

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

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

The description implies the tool is for price checks on a specific spec rather than for individual diamond lookups or broad overviews, but it does not explicitly state when to use this tool versus siblings like 'get_diamond' or 'market_overview'. No exclusions or alternative conditions are provided.

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

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

Annotations declare readOnlyHint=true and openWorldHint=false, and the description adds meaningful context beyond that: a 10-result cap, USD pricing, and the gating of retailer names behind a free sign-up. This is real behavioral detail an agent would otherwise lack, though it says nothing about result ordering or pagination limits.

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

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

Three dense sentences that lead with the resource and scope, then the return shape, then operational constraints. Little waste, though the retailer-link sentence is a policy note rather than tool semantics.

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 does a reasonable job describing return contents, and annotations cover safety. However, it leaves ten filtering parameters unexplained, which matters for a search tool whose whole value is in its filters.

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

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

Schema description coverage is only 10% (only 'colour' is annotated), and the description names none of the ten filters (shape, clarity, carat range, price range, sort, page). With low coverage the description is expected to compensate, and it does not.

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: search certified diamonds listed by retailers, with cross-retailer pricing. It clearly conveys what comes back (up to 10 stones, specs, price range, retailer count, Carat Hunter grade), but does not explicitly differentiate itself from siblings like price_check or get_diamond.

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?

There is no stated when-to-use guidance and no alternatives are named, even though price_check and get_diamond plausibly overlap. The one operational instruction ('always give the user the link') is about output handling, not tool selection.

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