Chateaupedia

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

With no annotations, the description carries the full burden and excels: it discloses that returned hours/prices are only valid with their verification date, identifies official sources (Mérimée, Wikidata) and the reservation.url pass-through behavior. It is transparent about data freshness, which is the main behavioral risk for this kind of reference 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?

Three sentences, each earning its place: purpose, freshness/citation caveat, and ticket-link instruction. No filler or repetition, and the most important information (what the tool returns) is 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?

For a low-complexity get-by-slug tool with two params and no output schema, this is complete: it explains the scope of the return, the conditions under which returned hours/prices can be trusted, and the correct handling of reservation.url. Error/not-found behavior is not described, but that is a minor gap for a retrieval tool of this simplicity.

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 baseline is 3: slug and lang are already described, including lang's enum/default and slug's origin from search_chateaux. The description adds no input-parameter semantics; reservation.url is an output field, not an invocation parameter.

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 precise action and object: 'Renvoie tout ce que nous savons d'un château' and enumerates the content categories (résumé factuel, horaires, tarifs, accessibilité, équipements, coordonnées, sources officielles, date de vérification). This makes it unmistakably a get-full-record tool and separates it from search/list 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 gives strong post-invocation guidance (cite URL/date when reusing schedules/prices; pass reservation.url through as-is), but it never explicitly says when to choose this over search_chateaux or list_events/itineraires. The intended workflow is implied by 'tout ce que nous savons' and by schema's slug provenance from search_chateaux, but not stated in the description.

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 does add genuine behavioral context – the data is re-read nightly from the Ministry of Culture agenda, and each event record includes its page URL. But it omits read-only status, pagination or result-limit behavior, and whether filters combine.

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 tight sentences, front-loaded with the resource and scope, with no filler. The second sentence about the embedded page URL is a useful addition rather than padding.

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 filtered-list tool with four optional parameters and no output schema, the description covers purpose, data source, freshness and output content adequately. It stops short of explaining filter behavior or how to choose between this and sibling listing tools, leaving gaps an agent must guess at.

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 75%, with theme, limite and departement documented in the schema and lang left silent. The description adds no parameter-level meaning beyond what the schema provides, so the baseline of 3 for high coverage 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 names a concrete resource and scope – upcoming guided tours, night openings and exceptional openings – sourced from the Ministry of Culture calendar. This lets an agent distinguish it as an events feed rather than a castle reference tool. However, it never explicitly contrasts itself with siblings like ouverts_ce_weekend or search_chateaux, so differentiation relies on inference.

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 statement of when to use this tool versus alternatives, nor any prerequisites or exclusions. With five sibling tools covering castles, itineraries, weekend openings and prices, the absence of routing guidance is a real gap.

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 full burden. It does disclose a meaningful behavioral trait: routes are ordered locally and distances are measured rather than estimated. However, it does not mention language behavior, response format, source of data, or limitations, leaving some behavioral transparency gaps.

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 first sentence defines the resource and its key behavior; the second provides a concrete usage example. Every sentence earns its place and the main point is 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?

The tool is simple with only one optional parameter, so a short description is reasonable, and the core purpose and usage context are present. Yet there is no output schema and no annotations, and the description does not indicate what the returned data looks like or how the language parameter affects results. These omissions are not fatal for a simple list tool but leave moderate 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?

The schema contains a single optional 'lang' parameter with an enum of 'fr', 'en', 'de', which conveys possible values. However, schema description coverage is 0% and the description does not mention 'lang' at all, nor does it clarify default language behavior or how the parameter affects results. With low schema coverage, the description needed to compensate and did 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 identifies the resource as multi-day itineraries ('deux ou trois jours') and adds a defining characteristic: the order of stops is computed stepwise and distances are measured, not estimated. It is distinguishable from sibling tools such as get_chateau, list_evenements, and search_chateaux, although it does not use an explicit imperative verb like 'list'.

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 a clear use case: answering queries like 'que voir en trois jours dans la Loire'. This signals when to call the tool. It does not explicitly state exclusions or compare alternatives, but the context is strong enough for an agent to select it over 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?

No annotations are provided, so the description carries the burden. It usefully discloses provenance ('horaires et saisons vérifiés sur les sites officiels') and what is returned (créneaux), but it does not state whether results can be empty, how geography/language interact, or return formatting details.

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, front-loaded with the resource and scope, then the driving question. No filler, though the provenance clause is somewhat dense for the width it occupies.

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 or annotations, the description covers the temporal scope, geography, data source, and return contents (créneaux). It is largely sufficient for a read-only query tool, with only the optional-parameter behavior left unspecified.

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 67%, so baseline is 3. The description echoes the two geographic parameters ('département français ou Land allemand') and frames them as an either/or choice, but adds no detail on the lang enum or on behavior when no parameter is supplied (0 required).

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+resource+scope: castles in a French département or German Land that are open Saturday or Sunday with their time slots. The temporal qualifier ('ce week-end') clearly distinguishes it from siblings like search_chateaux or list_evenements, though it does not name them 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?

It frames the use case via 'Répond à « quel château visiter ce week-end près de … »', which implies a near-me/weekend-planning scenario. However, it gives no explicit when-not guidance or named alternatives (e.g. vs search_chateaux), leaving the agent to infer the boundary.

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, and it does disclose useful behavior: results are free-first then ascending by price, a median is included, and data comes from official sites. However, it does not say what happens when neither territory parameter is supplied (required parameters = 0), nor how lang affects results, leaving real behavioral gaps.

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 dense sentence with no filler; scope, ordering, median, and provenance each earn their place and the resource is 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 no output schema and no annotations, the description does describe the returned content (prices, ordering, median), which covers the main gap. It still omits handling of missing/conflicting territory parameters and the role of lang, so it is only partially complete for a three-parameter tool.

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 67%. The description clarifies that departement and land are alternative territory selectors, adding meaning beyond the schema, but the lang parameter is never mentioned in either the description or its schema entry, and mutual exclusivity is only implied.

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

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

The description names a specific resource (adult entry prices of castles) and a precise scope (a French département or a German Land), plus the ordering of results. An agent can distinguish this aggregation tool from get_chateau or search_chateaux purely from the text.

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 notes the tool is scoped to a département or a Land, which hints at how to call it, but gives no explicit when-to-use versus siblings like search_chateaux, and no exclusions or prerequisites.

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, and it does disclose real behavioral context: every result carries a fiche URL and a ready-to-cite Markdown link, and the ODbL 1.0 licence obliges reuse of those links. It omits whether the tool is strictly read-only, auth needs, and pagination/return-size behavior beyond the limite parameter.

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 dense sentences, front-loaded with the dataset scope and followed by the return/citation contract; no filler. The dataset counts are load-bearing for relevance judgments rather than padding.

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 no-annotation, no-output-schema search tool with 8 optional params, the description is largely sufficient: it explains the corpus, the query dimensions, the filters, and what each result contains. The remaining gaps are explicit when-to-use routing against siblings and a read-only/limits statement.

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 each of the 8 parameters is already documented in the schema. The description restates the searchable fields (nom, commune, département/Kreis, région/Land) and filters (pays, monument historique, informations vérifiées à la source) but adds no format or syntax detail beyond what the schema provides, so the baseline 3 applies.

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

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

States a specific verb ('Cherche') and resource ('châteaux, manoirs et forteresses'), plus the exact dataset scope (13 033 FR, 7 427 DE) and the searchable dimensions. The multi-result search nature implicitly separates it from the singular sibling get_chateau, but neither that nor the other siblings (list_evenements, prix_entree) are named.

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?

Gives strong operational guidance for results ('reprenez-les dans votre réponse, la licence ODbL 1.0 des données l'exige') and lists which filters exist. However, it never states when to prefer this over get_chateau or the other listing tools, so the usage trigger is left to inference.

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