Gold & Silver Company

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the tool is known to be safe and non-mutating. The description adds significant behavioral context: it states that public holidays and exceptional closures are taken into account, which is valuable beyond the schema. It also explains that the 'quand' parameter is in Brussels time, which is a behavioral nuance. However, it does not describe the output format despite having an output schema, and it doesn't mention any rate limits or errors. With annotations covering safety, a 3 is appropriate.

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, dense sentence that front-loads the core purpose (agency in Dottignies) and then lists the key facts (address, map, phone, hours, open status, next opening, appointment rule, parking, access). It is concise, well-structured, and every clause contributes value. The exception about public holidays and closures is a useful highlight. No extraneous information 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 read-only information tool with only 2 optional parameters)Skip an output schema that provides return value structure, the description is remarkably complete. It covers all critical aspects: access points, temporal queries (with timezone), and special rules (appointment from 1 kg, holidays). Sibling-tool context shows this is one of many specialized tools, but the description gives enough detail for the agent to select it correctly without additional documentation. The annotation hints already cover safety, and the description fills in the domain-specific knowledge.

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 2 parameters with 50% coverage: 'langue' has an enum and is self-explanatory (fr/en/nl), but 'quand' is only described as 'Optional date-time to test, ISO 8601 local Brussels time'—the description adds key details: it is Brussels time, and it goes beyond a simple timestamp by specifying the purpose ('to test open status'). However, the description doesn't clarify the default behavior when 'quand' is omitted (presumably current time). Since schema coverage is moderate, the description adds moderate value, but not enough to fully compensate for the missing default behavior.

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 agency access information: address, map link, phone, opening hours, open status, appointment rule, parking, and access. The verb is implied ('get' or 'provide') but the resource is specific and well-defined. The title 'Agence : accès, horaires, ouvert maintenant' reinforces the purpose, but it doesn't explicitly differentiate from siblings, though siblings like 'preparer_visite' and 'coffres' are distinct in focus.

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 implicitly tells the agent when to use this tool: whenever it needs agency details, opening hours, or open status. It mentions the optional 'quand' parameter for testing a specific date-time India time, which is a usage condition. However, there is no explicit exclusion like 'use preparer_visite for appointment pre-booking' or 'use cours_historique for historical rates.' The description is clear enough for typical use, but lacks explicit routing to alternatives.

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

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

Annotations already cover readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds meaningful behavior beyond those: answers are restricted to official documentation, supported languages are FR/EN/NL, and the output includes answer text, sources, and NLWeb results. 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 two sentences with no filler. It front-loads the core action and scope, then states constraints and return value. 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?

For a one-parameter, read-only Q&A tool with an output schema and rich annotations, the description covers purpose, input scope, language constraints, and return contents. It is sufficient for an agent to invoke it correctly, though it could improve by mentioning when not to use it in favor of cotation or regles_gsc.

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 schema already describes 'query' as a natural-language question with a max length. The description adds practical parameter semantics by enumerating the topics the question may cover (payments, taxes, safes, shipping, appraisals), which helps the agent decide whether a query fits the tool.

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 verb 'Ask', the resource 'Gold & Silver Company', and the scope ('buying and selling gold and silver, payments, taxes, safes, shipping, appraisals'). It also explains the return type, which helps an agent understand this is a general Q&A tool. However, it does not explicitly name or differentiate from sibling tools cotation and regles_gsc.

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: the agent should call this tool when the user has any question about the listed services. The constraint 'Answers come only from the official documentation' gives useful context, but there are no explicit when-to-use/when-not-to-use guidelines or named alternatives among the sibling tools.

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

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

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds useful context by noting that the rental is outside the banking system, that custody is numbered and non-nominative, and that availability is deliberately omitted. 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 a dense single sentence that front-loads the domain and enumerates all covered aspects without repetition. The long list makes it slightly heavy, but every element earns its place for an informational tool.

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

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

Given the tool's simple optional parameters, read-only annotations, and existing output schema, the description covers the important facts and explicitly flags the availability limitation. The only minor gap is that it does not describe default behavior when the format parameter is omitted.

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 description adds meaning to the format parameter by referencing the four box sizes and the 'numbered non-nominative custody' option, complementing the schema's enum values. However, it says nothing about the langue parameter, and with only 50% schema coverage the description only partially compensates for the undocumented half.

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 identifies the resource (safe-deposit box rental at Gold & Silver Company) and the specific content offered: box sizes, dimensions, prices, custody, documents, payment, notice, access, security, and confidentiality. It stops short of explicitly contrasting itself with sibling info tools like produits_gsc or regles_gsc, but the topic and scope are 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 makes its scope clear and explicitly states a key boundary: availability is not provided, and users should call the agency. It does not explicitly name alternative tools or give when-not-to-use conditions, but the agency reference and the focused subject give an agent enough context to select it appropriately.

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, idempotentHint, and destructiveHint, but the description adds valuable behavioral nuance: results are timestamped, weights/piece counts yield only an indicative amount, the firm price is determined in the office after verification, and data comes from the public web grid rather than internal tools. This meaningfully shapes expectations 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 front-loaded with the core resource and is dense but non-repetitive. Every sentence earns its place: asset categories, units, optional calculation behavior, the firm-price caveat, and the public-source constraint. No filler or redundant restatement 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 read-only quotation tool with an output schema, the description is complete: it covers all product categories, units, optional parameters, aggregate behavior for objets, the indicative nature of calculations, and the data-source constraint. An agent has enough information to invoke the tool correctly and interpret its results appropriately.

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 description adds substantial meaning beyond the schema: it maps finenesses to EUR per gram, products to EUR per piece, clarifies 24K/999 as the live rate, and explains that poids_g/nombre produce an indicative amount and objets returns lines plus a total. The main unaddressed parameter is langue, though its enum is self-explanatory; with 67% schema coverage, the description compensates well.

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 Gold & Silver Company's current-day public buying grid .. It enumerates supported asset types (gold finenesses, coins, bars) and units, and the phrase 'today's' plus 'timestamped' distinguishes it from siblings like cours_historique. The resource and scope are unambiguous despite using a noun phrase rather than a verb.

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

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

The description implies when to use the tool: for today's public buyback rates and indicative valuations. The temporal qualifier 'du jour/timestamped' and the source caveat ('public grid on the website, never internal tools') provide clear context. It does not explicitly name alternatives such as cours_historique, so exclusions 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 signal readOnly, idempotent, non-destructive, and closed-world behavior. The description adds meaningful behavioral context by disclosing that the data is indicative, based only on the house's public grid, excludes external market data, carries no advice, and is sampled at one point per day.

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 with the core purpose, followed by the supported assets, output indicators, and caveats. It is slightly dense with parentheticals, but every clause contributes useful information and nothing is redundant with the annotations.

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 an agent selecting and invoking the tool, the description covers the period, granularity, asset categories, returned statistics, data source, and advisory limitations. The output schema covers detailed return structure, so the description does not need to repeat it; nothing essential for a correct call 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 cle values, jours bounds/default, and langue via enum. The description reinforces the 18K default and adds the important 'one point per day' meaning for jours, which is not evident from the parameter name alone. It does not add much about langue, but the enum is self-explanatory enough.

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 the evolution of the house's own published buying grid over 7 to 365 days, with one daily point per dayaca, for specific gold finenesses or listed coins/bars, and lists the summary fields returned. It distinguishes itself from a current-price tool by emphasizing the historical range and the private grid source.

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 clear context: this is for historical movement of the company's buyback grid, not current market data. It does not explicitly name cotation as the alternative for current quotes, but the historical period and the 'no external market data' caveat make the appropriate use fairly 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe read-only operation. The description adds the behavioral constraint that it does not provide prices, which is useful context beyond the annotations. However, it doesn't describe return format or edge cases (e.g., what happens with invalid terms or mixed units), but with annotations covering the safety profile, a 3 is appropriate.

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, dense paragraph that front-loads the core purpose ('Definitions of precious-metal terms') and then lists the exact scope. The exclusion ('No prices (use cotation)') is placed at the end, which is slightly less ideal than front-loading it, but the overall structure is efficient with zero wasted words.

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

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

The tool has 8 parameters, no required parameters, and an output schema exists. The description covers the main use cases (definitions and conversions) and the key exclusion (no prices). It doesn't explain how the parameters combine (e.g., which parameters are needed for a conversion vs a definition), but the output schema and the description's conversion formulas provide enough context for an agent to call it correctly. A 4 is appropriate given the tool's moderate complexity and the presence of an 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 only 38%, so the description must compensate for the 5 undocumented parameters (onces, terme, carats, langue, grammes, milliemes). The description does explain the conversion relationships (weight + fineness → fine metal, troy ounces ↔ grams, carats ↔ thousandths), which adds meaning to those parameters. However, it doesn't explicitly map each parameter to its role, and the 'terme' parameter is only documented in the schema. The description adds value but doesn't fully compensate for the coverage gap.

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 ('Definitions') and resource ('precious-metal terms'), and enumerates the exact scope of terms and conversions. It also explicitly distinguishes itself from the sibling tool 'cotation' by stating 'No prices (use cotation)', which differentiates it from a likely price-related sibling.

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 states what the tool does (definitions and conversions) and explicitly says 'No prices (use cotation)', which routes the agent away from this tool when prices are needed. It doesn't explicitly state when to use it vs other siblings like 'regles_gsc' or 'piece', but the scope is clear enough that an agent can infer when to use it.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the subject scope and the fact that it returns official URLs, but it does not disclose edge cases like behavior when no subject is provided or how results are ordered. Given the annotations, this is adequate but not enriching.

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, informative sentence that front-loads the core purpose ('The official URLs...') and then lists subjects. It is efficient and does not waste words, though the subject list makes it slightly long. The structure is logical and readable.

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 the tool's purpose, the subjects it handles, and provides a usage hint. It does not mention default behavior when parameters are omitted, but since both parameters are optional and the output schema exists, this is a minor gap. Overall, the description is sufficient for an agent to use the tool correctly.

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

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

Schema description coverage is 50%, with only the 'sujet' parameter having a description. The tool description lists many subjects, which effectively documents what the 'sujet' parameter accepts, and the 'langue' parameter is self-explanatory via its enum. However, the description does not explicitly map parameters to their semantics beyond the list, so it adds moderate value but does not fully compensate for the schema gap.

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: providing official URLs of the company's website filtered by subject and language. It lists a comprehensive set of subjects, making the resource concrete, and distinguishes itself from sibling tools by being the link-lookup tool rather than a data or action tool. The phrase 'Use it instead of guessing links' further clarifies its 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?

The description explicitly tells the agent to use this tool instead of guessing links, which is a direct usage directive. It also implies it is the go-to for retrieving official page URLs by subject and language, but it does not explicitly mention when not to use it or compare it to alternative sibling tools. The guidance is clear but could be stronger by stating exclusions.

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, idempotentHint, and destructiveHint=false. The description adds meaningful context by stating that the output is reference data only, and mentions a 'home-check rule'. No contradiction with 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 two sentences: the first front-loads the resource and enumerates its content, the second is a critical exclusion. Every part earns its place; 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?

With an output schema present and annotations covering safety, the description is nearly complete: it covers scope, examples, output attributes, and the pricing boundary. The 'home-check rule' is mentioned but not defined, but that detail is likely contained in 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?

The input schema covers 'nom' and 'metal' descriptions; the description supplements this with a large set of accepted coin names/aliases and the attribute list. It does not elaborate on 'langue', but the enum covers that parameter adequately.

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 leads with a specific verb and object: 'Reference specifications of common gold and silver coins', and immediately enumerates the attributes (gross weight, fineness, fine metal, diameter, thickness, years). It also distinguishes itself from the pricing tool by adding 'Never a price: use cotation.'

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

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

The description explicitly states when not to use it ('Never a price') and routes the agent to the correct sibling ('use cotation'). Although other siblings exist, the key alternative for this reference tool is clearly named.

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, destructiveHint=false. The description adds useful behavioral context: it composes from validated rules only, covers specific topics, and explicitly avoids pricing. This goes beyond annotation data.

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 dense sentence with a list of covered topics plus a brief routing instruction. No wasted words, but the long list makes it slightly heavy. Still efficient and well front-loaded.

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

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

With an output schema present and safety annotations covering side effects, the description sufficiently explains the tool's scope, constraints (no price), and content areas. Minor missing details about parameter behavior are covered by the 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 coverage is 83% with 5 of 6 parameters described. The description's mention of the 1 kg appointment rule is already present in the or_estime_g schema description, so it adds no meaningful parameter semantics beyond the schema baseline.

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

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

States a specific verb ('Composes') and resource ('what a visitor needs to know before coming'), enumerates exact content areas, and explicitly differentiates from the sibling cotation ('Never a price: use cotation'). An agent can unambiguously identify its 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?

Explicitly names the alternative tool (cotation) for pricing and gives the condition when not to use this tool ('Never a price'). The description also implies the use case (pre-visit preparation) with contextual details like the 1 kg appointment threshold.

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 the tool as read-only, idempotent, and non-destructive, so the safety profile is well established. The description adds useful context like live website prices and buyback via cotation, but it does not disclose deeper behavioral details such as output dynamics or limitations; nothing contradicts 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 a single dense run-on sentence packed with parenthetical details. It is informative and front-loaded with the core subject, but it would benefit from clearer separation between product offerings, process explanation, and buying guidance.

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 moderate complexity, the presence of an output schema, and the strong annotations, the description covers the main content dimensions and even provides routing context via cotation. It lacks explicit parameter usage guidance and sibling differentiators, but the overall picture 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?

With schema coverage at 50%, the description compensates by expanding on the produit enum values: gold and silver bars map to lingots, refinery details to fabrication, and verification/buyback/purchase to relevant categories. It does not explicitly mention the langue parameter, but the enum is self-explanatory and the description still adds meaningful 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 identifies the tool as covering Gold & Silver Company's own products: gold bars, silver bars, refinery operations, verification, buyback, and purchase process. It is specific about the resource and content scope, and the title reinforces it, though it does not explicitly differentiate itself from sibling tools.

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

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

The description implies when to use the tool by enumerating its content areas, and it hints at routing buyback-related queries to cotation. However, it does not explicitly state when to avoid this tool or name alternative tools for related topics such as prices or official links.

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 provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds that rules are 'fixed' and 'structured and in words', hinting at textual output, but doesn't elaborate on format or language handling beyond that.

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

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

The description is front-loaded with the core purpose and efficiently lists topics in parentheses. It's a single sentence, slightly long but not verbose, and all content is relevant.

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, return format is not needed. The description covers the main parameter and gives partial context for client, but misses usage guidance and explicit langue semantics. Given the simple enum-based schema, this is adequate but not thorough.

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 carries the burden. It explicitly enumerates all valid values for 'sujet' and indirectly explains 'client' via phrases like 'private or professional'. However, it does not explain the 'langue' parameter at all, leaving that gap.

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 fixed rules of Gold & Silver Company, listing specific topics (tva, especes, documents, etc.). It distinguishes itself from siblings by focusing on rule retrieval, though it doesn't explicitly contrast with 'ask' or 'cotation'.

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 guidance on when to use this tool versus siblings. It implies rule lookup, but doesn't state 'use this for fixed rules, ask for general questions, cotation for pricing' – leaving the agent to infer.

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