Socle — Baltic & Finnish architecture (P.-J. Tribot)

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

With no annotations supplied, the description carries the transparency burden and does well by listing the returned fields for each entity type. However, it does not mention read-only behavior explicitly, permission requirements, rate limits, or how missing or invalid ids 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?

The description is front-loaded with the core purpose and then supplies useful field and identifier details. It is dense but not wasteful; a slight structural improvement would be splitting the long parenthetical field list into shorter sentences.

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?

There is no output schema, so the description appropriately explains what a returned record contains for each entity type. It covers accepted identifiers and return content well, though it lacks not-found or error behavior, which would complete the picture for an agent.

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 defines the single id parameter. The description adds value by naming the source of valid ids and providing examples such as 'lieu/riga-alberta-iela-4' and 'person/alvar-aalto', which clarify accepted identifier formats 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 states a specific retrieval purpose: a full record of one entity from the architecture entity base. It distinguishes the three entity types and explicitly connects the id to search_baltic_finnish_architecture, which separates it from the sibling search tool.

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 clearly indicates the tool is for fetching a full record by an id returned from search_baltic_finnish_architecture or by Wikidata QID. It does not explicitly state when not to use it or name alternatives beyond the search tool, so it is strong but not fully explicit about usage boundaries.

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 supplied, so the description carries the full burden. It does add the meaningful trait that the entire text is returned ('texte intégral'), implying no truncation or summarization, but says nothing about error behavior for an unknown id, response size, or partial/absent notes.

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 return behavior stated first and the id provenance in a compact parenthetical. Nothing is redundant and no sentence is wasted.

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 tool with no output schema, the description covers what the tool returns (full note text), what the parameter is, and where to get it. Only edge-case behavior for invalid or missing ids is left unaddressed, which is a minor 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?

Schema coverage is already 100%, so the baseline is 3, but the description earns credit by explaining the provenance of id (returned by search_corpus) and giving a concrete example format ('souverainete-cognitive'), which clarifies the slug convention beyond the schema's terse 'Identifiant de la note (slug)'.

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 verb and resource — 'Renvoie le texte intégral d'une note' — and scopes it to Pierre-Jean Tribot's corpus. It clearly distinguishes this retrieval tool from the sibling search_corpus by positioning itself as the follow-up call that fetches a single note's full 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 gives explicit workflow context: the id comes from the 'champ id renvoyé par search_corpus', which tells an agent both when and how to use this tool. It stops short of stating exclusions (e.g. when to prefer get_architecture_record instead), so it is clear but not fully comparative.

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 does well: it discloses the ordering algorithm (nearest-neighbour from a start point), that distances are as-the-crow-flies, that links to records and any matching editorial route are returned, and what the default start point is. It does not explicitly state the operation is read-only with no side effects, nor what happens on empty result sets.

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 plus an example block: the core action and selection modes come first, the return shape second, and motivation examples last. Nothing is padding, and the examples earn their place by anchoring ambiguous itinerary phrasing.

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 8-parameter tool with no output schema, the description does the necessary work by describing the returned payload: ordered stops, crow-flies distances, record links, and matching editorial routes. The remaining gap is that the interaction between filters (intersection vs union) stays ambiguous under 'and/or', and no-result behaviour is unaddressed.

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 every parameter is already documented, and the description largely restates the filter dimensions (architect, city, collection, era, ids) rather than extending them. It does add the combination behaviour 'and/or' and the start-point semantics, but that is marginal over an already complete schema — 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 and resource — 'Plan a visit route through buildings' — and immediately scopes the corpus to the Baltic states and Finland. It is clearly distinguishable from the sibling search_* tools because it produces an ordered itinerary rather than a result 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?

Explicitly says 'Use it for itinerary questions' and supplies three concrete query examples (Riga day, Aalto route, Vilnius modernism walk), which gives an agent a clear trigger. It never states when NOT to use it, e.g. that plain lookups should go to search_baltic_finnish_architecture or get_architecture_record, so the routing to siblings is left implicit.

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 are absent, so the description carries the full burden. It usefully discloses data provenance (identities verified against Wikidata), corpus size, and that results are ids for get_architecture_record, but it omits auth/permission needs, rate limits, result ordering, and pagination behavior beyond the k parameter. Moderate disclosure for a read search 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?

Purpose is front-loaded, but the sentence is bloated with long enumerations of cities, buildings, and entity counts, plus a redundant French restatement at the end. Much of that catalogue detail aids discovery but could be trimmed without losing call-critical information.

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 seven optional parameters, 100% schema coverage, and no output schema, the description covers corpus scope, matching behavior, filter purpose, and id-to-record chaining well. It leaves ranking and result-shape behavior implicit, but for a search endpoint that is a minor 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?

Schema coverage is 100%, so the baseline is 3; the description adds value by specifying that q matches local, English, and French names plus architects, styles, periods, and descriptions, which is meaning beyond the schema's generic 'free text' wording. It also clarifies that filters are optional and may substitute for q.

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 ('Search') and a clearly bounded resource (an architecture entity base covering the Baltic states and Finland), and names get_architecture_record as the follow-up for returned ids. It does not explicitly distinguish itself from the sibling search_corpus, which is the one remaining ambiguity, so it falls just short of a 5.

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?

Offers some in-context guidance ('Can be empty if filters are set' for q, 'Use this to compare cities' for era) and notes filters are optional. However, it never says when to prefer this tool over search_corpus or when not to use it, so the alternatives comparison 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.

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

No annotations are supplied, so the description bears the full burden. It does disclose the return shape (titre, URL, extrait) and that results are relevance-ranked ("les plus pertinentes"), but says nothing about search mechanics — keyword vs semantic, language of the corpus, whether full text or abstracts are matched, or cost/latency 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 compact sentences with zero filler, front-loading the corpus identity before return values and the citation rationale. The parenthetical topic list is slightly long but earns its place by scoping what the corpus covers.

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 two-parameter read-only search with fully documented schema and no output schema, the description covers corpus scope, return fields, and intended use. It leaves only secondary details (ranking method, corpus size/language, result-count behavior) unstated.

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%: both q and k (with its 1–12 range and default 5) are documented in the schema itself. The description adds only the implied relevance framing ("les notes les plus pertinentes"), which does not extend parameter meaning beyond the schema, so 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 ("corpus de notes de Pierre-Jean Tribot"), and enumerates the thematic scope (IA, culture, patrimoine, géopolitique, etc.) plus what a result contains (titre, URL, extrait). It does not name the sibling it is not — notably search_baltic_finnish_architecture, another corpus search — so an agent must infer from the corpus name which search tool applies.

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 explicit usage guidance: "À utiliser pour citer sa pensée à la source plutôt que de la paraphraser de mémoire", which tells the agent the trigger condition (quoting sourced thinking instead of recalling from memory). No exclusions or named alternatives are provided, so it stops short of full when/when-not routing.

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