bordeaux.guru — Bordeaux en primeur & terroir

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

With no annotations, the description is the only source for behavioral context, and it does reveal that this is an informational 'about' tool that covers categories like en primeur tasting notes, climate, phenology, terroir, access tiers, and links. It does not mention output format or limitations, but for a no-side-effect, no-parameter overview tool this is relatively complete.

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 one compact, front-loaded sentence that states the purpose and immediately enumerates the main content areas. Every phrase earns its place without filler or redundancy.

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 parameter-less tool with no output schema, the description covers all relevant information an agent likely needs: what the overview contains and how to get it. It also makes clear that this is not a data-retrieval tool, which is sufficient given the sibling 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 tool has zero parameters, so the schema already fully represents the input contract. The description adds no parameter-specific details, which is appropriate given there are none, so the baseline of 4 applies.

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

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

The description clearly identifies the resource as a high-level overview of the bordeaux.guru server's data coverage, access tiers, and links. This goes beyond a simple restatement of the tool name and helps an agent see that it is distinct from the get_* data retrieval tools. However, it relies on a noun phrase rather than an explicit verb describing what the tool itself returns.

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 says to use this tool when you need an overview of available data areas, access tiers, and links, rather than when fetching a specific château or tasting note. It gives a clear context but does not explicitly name sibling alternatives or provide exclusionary 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?

No annotations exist, so the description carries the full behavioral disclosure burden. It communicates that the tool computes aggregates and is restricted to Collector/Cellar members, which is helpful. However, it does not describe the output return format, how missing data is handled, or confirm the operation is read-only—leaving room for an agent to guess about runtime behavior.

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

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

The description is two sentences with no filler. The main purpose and metric examples are front-loaded; the access restriction follows cleanly in the second sentence. Every part earns its place and is easily scannable.

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

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

Given the simple two-parameter schema and no output schema, the description covers the essential context: comparison granularity ('appellations and/or vintages'), metric categories, and audience restriction. Minor gaps remain, such as not clarifying whether both parameters must be provided and not describing the actual return structure beyond passive aggregates, but these do not block reasonable 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 100%, with both 'years' and 'appellations' and 'appellations' having clear comma-separated descriptions. The description adds only a rough relationship between the parameters ('and/or vintages') but no additional format details, default behavior, or examples beyond the schema. This matches the baseline for fully schema-described parameters.

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, 'Compare,' and a specific resource: growing-season climate aggregates across Bordeaux appellations and/or vintages. Listing example metrics (GDD, heat days, rain, sunshine, ET0) further clarifies the domain. This clearly distinguishes it from sibling 'get_' tools, which retrieve singular records rather than perform comparisons.

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 first sentence clearly implies the use case: use this tool when a comparison of growing-season climate summaries is needed, whether across appellations, vintages, or both. 'Collector/Cellar members only' offers a concrete access constraint. It does not explicitly name alternatives, but the comparative scope is clear enough to avoid mistaking it for a single-season retrieval.

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; it discloses the returned content (profile fields and tasted wines) but doesn't state output format, error behavior, or non-mutating guarantees. 'Get' implies reading, and the content list helps, but security/behavioral details remain unspoken.

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 compact sentence with a front-loaded verb and resource, followed by a tightly listed set of included data. No filler or redundant restatement of tool name.

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, straightforward read tool, description is reasonably complete: it names the external source and lists returned data. Minor gap of not clarifying response format, but schema covers input and the profile scope is clear.

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

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

Schema description coverage is 100% with an illustrative example ('chateau-lynch-bages' or 'Lynch-Bages'). Description adds no additional parameter detail, so 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?

Description specifies verb and resource: 'Get a château profile from bordeaux.guru', plus enumerates contents (appellation, classification, terroir, vineyard size, typical blend, tasted wines). This clearly distinguishes it from exclusive sibling tools like get_terroir, get_tasting_note, or get_vintage_profile.

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?

Description implies usage for broad château overview through the word 'profile' and its comprehensive content list, but it doesn't explicitly state when to use this over narrower siblings or mention any when-not-to-use 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?

With no annotations, the description carries the full burden of explaining behavior. It discloses the data source and storage context (Open-Meteo/ERA5 via bordeaux.guru) and the three return modes: summary, monthly, and daily. It stops short of describing edge cases, season boundaries, units, or error behavior, but the key behavior is clearly presented.

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

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

The description is dense but front-loaded: it states the core purpose first, then lists relevant metrics and return modes. The parenthetical source explanation is useful, and no sentence is wasted, though the combined clause is somewhat packed.

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 use case, parameter context, and return granularity, which is adequate for a basic climate retrieval. However, with no output schema, an agent still lacks detail about exact season date ranges, units of measurement, valid appellation values, and behavior for unavailable data.

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

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

Schema description coverage is 100%, so the schema already documents appellation, year, and granularity. The description's mention of summary, monthly, and daily granularities largely mirrors the schema, adding little independent meaning beyond context.

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 a specific resource: growing-season climate for one Bordeaux appellation and year, and lists the data types it returns. It does not, however, explicitly contrast itself with sibling tools like compare_climate, so sibling differentiation is only implicit.

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 phrase 'for a Bordeaux appellation and year' implies the intended call for a single appellation/year climate query. The description gives no explicit guidance on when not to use it or when to prefer a sibling such as compare_climate.

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?

No annotations are provided, so the description must disclose behavior itself. It usefully states the data provenance, château brochure digitization, and the access-tier difference between aggregate and per-parcel results. It does not cover error behavior, membership authentication, or response formatting, but for a primarily read-like data lookup 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 purpose is front-loaded and the access distinction is expressed in a compact sentence. The parenthetical about digitized official château data adds credibility, though the odd quoted phrase 'údaje château' contributes little and keeps this from a perfect score.

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 tool with no output schema, the description provides enough shape: aggregate varieties for everyone, and per-parcel variety × soil × hectares for members. It is mostly self-contained, though membership mechanics and return-structure details are left implicit.

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 only parameter 'chateau' is already fully described in the schema, including an example, so the description does not need to compensate for missing parameter documentation. The description adds no new parameter semantics beyond the general subject matter, which matches a 100% schema-coverage 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?

The description clearly identifies the resource: parcel-level grape varieties for a Bordeaux château, and it clarifies the output scope by separating aggregate data from per-parcel member data. It is more specific than a tautology, but it does not name a sibling tool or use an explicit verb, so it stops short of maximum differentiation.

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

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

The membership distinction gives usable context: aggregate results are available to everyone, while variety × soil × hectares detail is gated to members. However, it does not say when to prefer this tool over related tools such as get_terroir or get_chateau, leaving some selection decisions to inference.

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 behavioral disclosure burden. It warns that data is sparse and available only for documented vintages, and it indicates that the source is official château brochures, setting expectations about coverage and provenance without revealing internal state.

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-loads the core resource and data phases, and caps usage expectations with the sparse-data caveat. No sentence is wasted; everything included supports invocation decisions.

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 optional-parameter getter with no output schema, the description conveys the fundamental return intent (phenology windows) and important coverage limitations. It lacks explicit output formatting details, but the schema plus this description give an agent enough to reason about the call.

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 covers both parameters completely with descriptions, so no additional semantic burden falls on the tool description. The phrase 'for a Bordeaux vintage' hints at the vintage parameter but adds no detail beyond the schema's own 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 clearly identifies the resource as vine phenology windows (budbreak, flowering, veraison, harvest) for a Bordeaux vintage. It effectively distinguishes itself from broader tools like get_vintage_profile or get_climate_season by anchoring the data source and scope, though it does not name a sibling explicitly.

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 'Sparse, documented vintages only' caveat implies when the tool will be useful, but there is no explicit guidance on when to choose this over get_vintage_profile or get_climate_season. The optional appellation and vintage parameters give some context, but no alternatives are 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?

Since no annotations are provided, the description carries the full burden, and it does meaningful work: it identifies the source, the returned tasting-note sections, and the tier behavior ('Free tiers receive a teaser'). It does not detail error cases or authentication, but for a read-only retrieval tool this is reasonably transparent.

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 one dense, front-loaded sentence with no filler words. It states the purpose, the resource, the output scope, and the tier limitation without repetition.

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

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

For a simple two-parameter read tool with no output schema, the description is unusually complete: it names the output fields and warns about teaser limitations for free tiers. The main missing context is sibling-selection guidance, which is already penalized under usage guidelines.

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%, so the schema already documents both parameters. The description adds context by framing them as 'one wine and vintage,' but it does not meaningfully enrich the schema-provided meaning.

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 begins with a specific verb and resource: 'Get the en primeur tasting note for one wine and vintage from bordeaux.guru.' It also enumerates the returned content, which makes it clearly distinct from sibling tools like get_chateau, get_vintage_profile, or search_wines.

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 does not state when to choose this tool over alternatives or when not to use it. It implies that it is for a single wine/vintage tasting note, but it does not mention exclusions, prerequisites, or routing to siblings such as search_wines for unknown wine names.

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?

No annotations are provided, so the description carries the behavioral disclosure burden. It does disclose meaningful output composition and data sources: 'real Copernicus DEM', 'BRGM gravel terraces (Dubreuilh types 1–6)', and 'lieux-dits coverage.' It does not state that this is a read-only lookup, does not mention caching, errors, or how 'coverage' is represented, and the 'get' verb only implicitly signals safety.

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, front-loaded sentence contains the core purpose and all relevant content dimensions without filler like 'useful' or 'comprehensive'. It is slightly awkward and compressed in the final clause, but every part contributes meaningful differentiation.

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 a single required parameter and 100% schema coverage, this is close to complete: the description tells an agent what kind of object it will receive and what thematic layers are included. The lack of output schema references a few unspecified conversion details, but the practical invocation context is covered.

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 parameter schema already fully documents `appellation` with an example, so the description is not required to add much here. The description repeats that the appellation is Bordeaux-specific but does not enrich the parameter semantics beyond the existing 100% schema coverage.

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

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

The description uses a specific verb plus resource: 'Terroir profile of a Bordeaux appellation'. It then enumerates the exact content—dominant soils, microclimate, relief, BRGM gravel terraces, and lieux-dits coverage—so it is far more specific than a generic 'get terroir' statement and can be distinguished from climate-only or wine-related siblings.

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 used when a terroir profile of a Bordeaux appellation is needed, listing the exact output categories. However, it gives no explicit when-to-use or when-not-to-use guidance and does not mention alternatives such as get_climate_season or lookup_lieudit, even though those are closely related 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, the description carries the behavioral burden. It clearly signals a read-only lookup and adds the useful coverage limit, but it does not describe edge behavior for unsupported years, format details, or any other constraints beyond the coverage warning.

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 every phrase earns its place: the action, the resource, the result contents, and the key limitation are all present. No filler or repetition.

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

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

For a single-parameter retrieval tool with no output schema, the description is nearly complete. It supplies what the tool returns and the coverage caveat. A slightly stronger answer would state the behavior when an uncovered year is requested, but this is not a critical gap.

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 documents the year parameter with an example, so the baseline is 3. The description adds meaningful value by stating that only covered vintages are returned, which directly informs the agent that some year values are invalid or yield no result.

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: it gets the bordeaux.guru vintage profile for a year. It enumerates the content (quality assessment, harvest summary, key events), which makes the tool's scope clear and separates it from siblings that cover terroir, phenology, or tasting notes.

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 it: when you need a vintage-level assessment for a given year. It does not explicitly discuss alternatives or say when to prefer tools like get_phenology or get_climate_season, and it only implies the coverage constraint rather than framing it as a selection rule.

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?

No annotations are provided, so the description carries the burden of behavioral disclosure. It adds useful context about the origin of the data and gives concrete examples, but it does not describe behavior such as whether matching is fuzzy, case-insensitive, or limited, nor does it mention what the output looks like. For a read-only lookup these gaps are minor but still worth noting.

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 with every clause earning its place: purpose, scope, data source, examples, and search dimensions. It is front-loaded with the main action and resource, making it 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?

For a simple read-only lookup with two optional parameters, the description plus schema covers the common use cases well. It does not explicitly describe the return shape or list fields, which would be more valuable given no output schema is present, but the verb 'Look up' and the known resource type make the output fairly predictable.

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

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

The input schema has 100% description coverage for its two parameters, so the schema already explains 'name' and 'appellation' with defaults and clear semantic hints. The description adds only a high-level summary ('Search by name and/or appellation'), which does not go beyond the structured field descriptions.

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 a specific verb ('Look up'), a resource type ('named vineyard sites / lieux-dits'), a geographic scope ('in Bordeaux appellations'), and the data source ('cadastral open data mapped by bordeaux.guru'). This makes it easy to distinguish from sibling tools like get_terroir, get_parcel_varieties, or search_wines without needing to inspect schemas.

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

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

The description provides clear context on how to use the tool: 'Search by name and/or appellation.' It implies that omitting one of the parameters is valid, and the schema further clarifies the omit-to-list behavior. It does not explicitly name alternative tools or say when not to use it, but the lookup scope is distinct enough from its siblings.

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

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

No annotations are present, so the description carries the transparency burden. It discloses the data source and the fields returned, which is helpful. However, it omits behavioral details such as whether results are ordered, limited, paginated, or how partial matches are handled.

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 intentionally shaped sentences with zero redundancy. The action, scope, and return-value summary are front-loaded, and 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 straightforward search tool with fully documented parameters and no output schema, the description gives enough for an agent to invoke it — the return format is summarized and the source scope is defined. Minor missing details like result limits or exact-match behavior prevent a higher score.

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 reported at 100%, so the schema already documents all four parameters well. The description does not need to repeat them; it adds only the useful context that 'query' maps loosely to wine name, château, or appellation, which is a nice corroboration but not a substantive addition.

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 ('Search'), a clear resource ('Bordeaux wines from bordeaux.guru en primeur tastings'), and searchable criteria ('name, château or appellation'). It also lists return fields, which clearly sets it apart from sibling getters like get_chateau and get_tasting_note.

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 the tool's purpose obvious — it is the free-text or filterable search tool for Bordeaux wines. However, it never explicitly says when to prefer this over siblings like get_chateau or get_tasting_note, nor does it mention exclusions or alternatives.

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