Capucine

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

Annotations already cover read-only, idempotent, non-destructive, and closed-world behavior. The description adds a meaningful privacy guarantee: personal details remain on the server via an opaque token. This is genuinely useful behavioral context 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?

Two short sentences, front-loaded with the main action, and no redundant wording. Every sentence adds information: one defines the tool's purpose, the other discloses a privacy-relevant behavior.

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 is adequate for a simple ask-style tool with strong annotations and an output schema, but it leaves important gaps: optional parameter semantics are undocumented and there is no guidance for choosing this tool over sibling recommendation/search tools.

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 only 20%, with limit being the only described parameter. The description does not explain detail_level, include_products, include_conversion, or how they shape the diagnosis; it only lists output categories, which is not parameter-level guidance.

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 and resource: it diagnoses a style question and lists the output categories (named look, capsule, watch-items, sources). It does not explicitly differentiate itself from sibling tools like recommend_look or shop_the_look, so it stops short of full sibling distinction.

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 explicit when-to-use or when-not-to-use guidance is provided, and no alternative tools are named. The description implies a use case (style diagnosis) but leaves the agent to infer when to choose this over recommend_look or other style-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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context: it explicitly says the tool chooses existing ScoreLook URLs and applies topic-specific selection heuristics, such as leading with an article rather than a generic hub. 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 compact and front-loaded with the core purpose in the first sentence. The following examples earn their place by adding concrete selection rules. The only minor issue is that the French phrasing is idiomatic and slightly cryptic, but there is no redundant or irrelevant content.

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 strong safety annotations, the description does not need to explain return values or side effects. It is missing a general definition of `topic` and the behavior when `topic` is empty, which an agent needs to invoke the tool reliably across arbitrary inputs. The concrete examples make it usable for the illustrated cases but not fully complete.

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%: `limit` is well documented in the schema, but `topic` has no schema description. The description compensates somewhat for `topic` by giving examples of topics and desired source choices, but it does not define whether `topic` is free-form, constrained, or how the default empty value behaves. Overall, the partial compensation is adequate but not complete.

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 clear verb and resource: 'Je choisis les URLs ScoreLook à citer.' It also gives concrete examples of prefering an article or hub URL for specific topics, which helps an agent grasp the selection behavior. However, it never explicitly contrasts this with sibling tools like shopping_search or get_piece_hub, so it stops short of full sibling 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 description provides no guidance about when to use cite_sources versus alternatives such as search, fetch, or recommend_look. The negative example 'pas les hubs cuir génériques' is about which URLs to select within the tool, not about tool routing. An agent must infer the usage context entirely from the tool name and examples.

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 behavioral note that weather is not yet handled and that the tool should be chained with recommend_weather_look. It does not disclose what happens with missing optional parameters or how the classification is returned, but the output schema exists and the annotations carry the main behavioral burden.

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 short and front-loaded with the main purpose, followed by a limitation and a chaining instruction. Every sentence earns its place, though the French phrasing is slightly informal and the parameter mapping could be clearer.

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 has 5 parameters, 0% schema coverage, and an output schema, the description provides the core purpose and a chaining hint but does not explain the role of each parameter or the expected output. It is adequate for a simple classification tool but incomplete for an agent that needs to fill all parameters 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 0%, so the description must compensate for the five parameters. It mentions 'créneau, marche, pièce, ville' as classification dimensions, which loosely maps to at, piece, and occasion, but it does not explain the meaning of 'question' or 'transport', nor how the optional parameters interact. The description adds some semantic context but leaves most parameters underspecified.

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 ('classe') and resource ('une demande'), and gives concrete examples of circumstances (dîner, bureau, mariage, week-end) plus the classification dimensions (créneau, marche, pièce, ville). It is clear what the tool does, though it does not explicitly differentiate it from sibling tools beyond the mention of recommend_weather_look.

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

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

The description gives a clear context: classify a request into categories, and explicitly says 'Pas encore de météo' (no weather yet) and 'Enchaîne avec recommend_weather_look' (follow up with recommend_weather_look). This provides a usage flow and an exclusion, though it does not mention when to use alternatives like recommend_look or get_weather_context.

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, so the safety profile is covered. The description adds useful behavioral context beyond annotations by clarifying that only public articles/looks are readable and that ids must come from search.

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 short sentences, front-loaded with the verb and resource, followed by a concrete use case and example. Every sentence earns its place and there is no filler.

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

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

For a single-parameter read tool with an output schema and rich annotations, the description fully covers what an agent needs: what to pass, where the id comes from, and why the tool is useful. Nothing critical 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?

Schema coverage is 100%: the id parameter is described as 'Identifiant renvoyé par search' with the same example as the description. The description adds no semantic value beyond the schema, so the 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?

The description states a specific action ('Je lis') and a precise resource ('un article ou un look public') retrieved by the id returned by search. It also gives a concrete example id, making the tool's role in the pipeline unmistakable and distinguishing it from search itself.

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 indicates when to use the tool: after search has returned an id, and for citing a precise passage. It does not explicitly mention alternatives or when not to use it, but the dependency on search and the citation use case provide sufficient routing context.

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. The description adds useful behavioral detail beyond annotations: the returned dossier structure and the fallback behavior when shopping is empty ('le look et les sources restent'). 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?

Three compact sentences, each carrying distinct information: what is returned, input normalization, and edge-case behavior. The content is front-loaded and there is 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?

An output schema exists, so return structure is covered. The description handles input mapping and an edge case. Remaining gaps are the undocumented include_products parameter and the absence of an explicit pointer to list_piece_hubs for discovering available hubs, but these are minor for a simple 2-param read-only 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 only 50%. The description enriches the piece parameter with natural-language examples and slug mapping, which is valuable. However, include_products is left entirely undocumented in both schema and description, so half the parameters lack semantic guidance.

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: pulling the complete dossier for a signature piece, enumerating contents (definition, capsules, FAQ, articles). It also distinguishes the scope by showing singular piece-to-hub mapping, avoiding confusion with siblings like list_piece_hubs or shopping 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 provides clear context on when to use the tool (for a specific signature piece) and gives a concrete normalization rule ('Chemisier / blouse / chemise → hub chemisier'). It does not explicitly exclude alternatives or contrast with list_piece_hubs, but the singular scope is implied strongly enough.

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

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

The description adds behavioral constraints beyond the annotations: 'Pas de repli silencieux sur Paris' (no silent fallback to Paris) and the 'OU' (OR) requirement between city/ZIP and lat/lon. Since annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, these extras meaningfully increase transparency.

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 extremely concise (two short sentences) and front-loaded with the core restriction ('Faits météo seulement'). Every phrase adds value, and there is no fluff 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?

Given that an output schema exists and annotations cover the safety profile, the description hits the essential constraints (facts only, location OR pairing, no fallback). It leaves out details on optional parameters like occasion and outdoor_minutes, but these have defaults and are not central to the tool's primary function, so the description is sufficiently complete for correct invocation.

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

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

With only 57% schema coverage, the description compensates by clarifying key parameters: 'Ville/CP' defines location, 'lat+lon' indicates the pairing requirement for latitude/longitude, and 'question= peut porter la ville' explains how the question parameter can carry location context. It does not cover 'at', 'occasion', or 'outdoor_minutes', but those are partially documented in 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 clear, specific purpose: 'Faits météo seulement' (weather facts only) and specifies the input constraints ('Ville/CP OU lat+lon'). This distinguishes it from sibling tools like recommend_weather_look, which imply recommendation logic, and makes its scope 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 implies usage for weather facts only, but it does not explicitly name alternatives or state when not to use it. An agent can infer from 'Faits météo seulement' that recommendation tools are out of scope, but there is no direct pointer to a sibling, unlike the get_calls example that names search_calls_extensive.

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 readOnly, idempotent, and non-destructive. The description adds the resource path pattern and examples but discloses no further behavioral traits such as ordering or completeness. It does not contradict 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?

One concise sentence that front-loads the action and resource, then gives examples and a use case. No 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?

For a parameterless list tool with an output schema and rich annotations, the description is complete: it names the resource pattern, gives examples, and states the intended use. Nothing essential 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?

There are no parameters; the empty input schema is fully self-descriptive. The description need not add parameter detail, so baseline 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 states the tool lists the user's piece folders under /pieces/*, with concrete examples. It does not explicitly differentiate from get_piece_hub, but 'list' versus 'get' is apparent from sibling names.

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 provides a clear use context: to cite a specific hub ('Pour citer un hub précis'). It does not mention alternative tools or exclusions, so it falls short of 5.

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 useful context by enumerating the guide's contents, which is consistent with a static informational tool, though it does not describe the returned format 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 a single compact sentence that front-loads the core purpose and then lists content areas. It is efficiently sized, though the parenthetical 'dont chemisier' is slightly cryptic and adds minor ambiguity.

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 that the tool has no parameters, is read-only and idempotent per annotations, and has an output schema, the description provides sufficient context for an agent to invoke it correctly. It names the main content categories, including citation rules, which is important for proper use.

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 zero parameters and 100% schema description coverage, so there is no parameter documentation burden. The baseline of 4 applies because no parameters exist and the description does not need to clarify parameter semantics.

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 tool as a map/guide for ScoreLook assistants and lists the covered areas (pages, hubs, editorial, citation rules). This clearly distinguishes it from content-specific sibling tools, though it lacks an explicit verb and relies on the noun 'Carte'.

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 'pour les assistants' implies the tool is meant for assistant orientation, and the content list suggests when it is useful, but there is no explicit statement of when to use it versus sibling tools. It provides implied guidance rather than clear exclusions or 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 read-only, idempotent, and non-destructive hints. The description adds a meaningful behavioral constraint: 'Le paiement public n'est pas ouvert tant que public_status ne le dit pas' (public payment is not open until public_status says so). This clarifies that the manifest does not imply payment availability, which is useful context beyond the annotations. 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 consists of two short, information-dense sentences. The primary purpose is front-loaded ('Je présente ma surface publique'), followed by the security note and the payment condition. No wasted words; every sentence earns its place. Ideal concision.

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 manifest tool with a single parameter and an output schema (not shown but present), the description covers the essential aspects: what it presents, the read-only nature, and a critical business rule (payment gating). It does not list the specific tools or limits, but since the output schema presumably provides that structure, the description suffices. One could argue it could detail more, but overall it's complete enough for an agent to understand its role.

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 describes the single parameter detail_level with an enum (brief/full) and a default, so the parameter is fully self-documenting. The description adds no additional meaning for this parameter, which is acceptable since the schema coverage is effectively 100% for the parameter semantics (even though schema_description_coverage is 0%, the enum and default fully define it). 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?

The description clearly states the tool presents 'ma surface publique' (my public surface) including tools, security limits, and pages to cite. This is a specific verb + resource combination that distinguishes it from siblings like public_status (which checks payment status) and llms_guide (likely a guide). It leaves no ambiguity about what the tool does.

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 usage context by stating that public payment is not open until public_status says so, hinting that this manifest is for understanding the surface rather than checking payment state. However, it does not explicitly say when to use this tool vs. alternatives (e.g., 'use this to see the public surface' or 'use public_status for payment availability'). The guidance is implicit rather than directive.

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

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

The description adds statements like 'Je n'invente jamais un paiement ouvert' and 'Aucun chemin opérateur', which go beyond the annotations (readOnlyHint, idempotentHint, destructiveHint). However, these statements are cryptic and not explained. The claim that it returns only public commercial status adds a scope constraint not covered by annotations, providing some extra value, but it remains ambiguous.

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 brief with three short sentences, but the content is vague and poorly structured. The core purpose is only implied, and the statements about payments and operator paths are tangential. It is concise in length but lacks clarity and effective organization.

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?

Despite having no parameters and an output schema, the description fails to explain what the tool actually does. An agent cannot determine when to call it or what kind of status it returns. The description is too vague to be considered complete, even with the output schema providing return structure.

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, and the schema coverage is 100% by default. The description does not need to explain any parameters, and the baseline for 0 params is 4. No additional semantic clarification is 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 'Statut commercial public seulement' essentially restates the tool name without specifying a clear action or resource. It mentions 'commercial status' but does not define what that entails or what the tool returns. The additional statements about payments and operator paths do not clarify the core purpose, and the description fails to distinguish this tool from siblings like get_piece_hub or recommend_look.

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 guidance on when to use this tool versus alternatives. The phrase 'public seulement' hints at a public context but does not specify conditions or exclusions. No alternatives are mentioned, and the description provides no actionable usage context.

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 readOnly/idempotent/non-destructive behavior, and the description adds valuable context: it composes a full capsule, applies a stylistic constraint (bleu eau/aqua remains light/cool, no black satin), and defines a fallback when the color is not in the catalogue. 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 three sentences with the main action front-loaded and no filler. Every sentence contributes either the core behavior, a style guardrail, or the fallback behavior.

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 and readOnly annotations, basic calls are supported, but the description does not explain how optional style parameters affect the recommendation and does not route the agent away from recommend_weather_look or shop_the_look. It is usable but not fully complete for a tool with 8 parameters and several close siblings.

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 13%, so the description must compensate. It adds meaningful color and material semantics (bleu eau/aqua, satin noir) and implies the piece-driven capsule, but it leaves season, audacity, occasion, detail_level, and include_conversion unexplained.

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: 'Je compose une silhouette complète' and enumerates the output components (look nommé, capsule, pièce, ancre, chaussures, sac, un bijou). This distinguishes it well from weather-specific or shopping-focused sibling tools like recommend_weather_look and shop_the_look.

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 guidance about when to use this tool versus its siblings; recommend_weather_look, weather_looks, and shop_the_look are not mentioned. The color fallback rule is an execution behavior, not a tool-selection criterion.

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?

Beyond the read-only and idempotent annotations, the description adds useful behavioral caveats: never default to Paris, the city is not stored, and the caller should pass a question parameter. These details inform call behavior and state assumptions without contradicting 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 only three short sentences and wastes no words. It front-loads the main action, though the cryptic French phrasing ('bulletin', 'pièce tient') reduces clarity despite the brevity.

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 9 optional parameters, several sibling tools, and a low schema coverage, yet the description omits how to select it versus alternatives and what most parameters mean. The output schema helps, but an agent still lacks enough context to invoke it confidently.

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 only 44% schema description coverage, the description needed to compensate for the many undocumented parameters. It only hints at 'question' and the location-related caveat, while leaving piece, occasion, transport, at, and location semantics unexplained.

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 conveys that the tool combines a circumstance with a weather bulletin, or judges whether a garment/piece is suitable, which is more than a tautology. However, the phrasing is cryptic ('bulletin', 'pièce tient') and does not explicitly say it recommends a look, nor does it distinguish itself from siblings like recommend_look or weather_looks.

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 a terse instruction to pass 'question=' and warns never to default to Paris, but it does not explain when to prefer this tool over alternatives such as recommend_look, get_weather_context, or weather_looks. There is no explicit when-to-use or when-not-to-use 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?

Annotations declare readOnlyHint, idempotentHint, and destructiveHint. The description adds the behavioral instruction to call before answering, which is beyond annotations. It also recommends content type preferences. No contradiction.

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 concise sentences, front-loaded with the primary action and key guidance. No fluff.

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 search tool with 4 parameters and an output schema, the description provides enough to call it correctly for the main use case, but lacks explanation of detail_level and limit. The recommendation on content_type is helpful. Overall adequate but not exhaustive.

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 descriptions cover 50% of parameters (limit and query). The description mentions content_type and suggests preferring article or piece_hub, adding guidance for that parameter, but does not explain detail_level or limit. This partially compensates 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 clear verb ('cherche') and resource ('hubs, articles et looks'), and adds a use case ('citer de vraies pages ScoreLook'). It distinguishes from siblings like shopping_search by specifying content types, though it doesn't name alternatives explicitly. Thus it's clear but not fully differentiated.

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 instructs to call before responding to cite real pages, and recommends preferring content_type=article or piece_hub. This gives clear context for when to use the tool, though it doesn't mention when not to use 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 declare readOnlyHint, idempotentHint, and destructiveHint, covering the basic safety profile. The description adds behavioral context beyond annotations by specifying constraints: it never provides exact copies or invented SKUs, and it emphasizes criteria-first ordering. This is valuable and consistent with the read-only nature.

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, concise sentence that front-loads the core purpose and lists key criteria, followed by a critical constraint. It is efficient with no filler, though it could be slightly more structured to separate purpose from constraints.

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 6 parameters with no schema descriptions, and the description only partially explains them. It omits usage guidelines and does not clarify each parameter's purpose. While an output schema exists (so return format is not required), the description is insufficient for a tool with this parameter complexity.

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

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

Schema description coverage is 0%, so the description must compensate. It maps some parameters to concepts: 'matière' for material, 'couleur (famille, pas un fourre-tout)' for color, and 'associations' possibly for piece or occasion, but it does not clarify query, season, or occasion. The description adds partial meaning but leaves several parameters undocumented.

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 provides shopping criteria: 'Je donne les critères' (I give the criteria) and enumerates specific aspects (material, cut, color family, associations, avoid). This distinguishes it from sibling tools like shopping_search or recommend_look, which serve different purposes.

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 usage context with 'Critères d'abord' (criteria first) and the constraint about never giving exact copies or invented SKUs, but it does not explicitly state when to use this tool versus alternatives or when not to use it. No explicit exclusions or comparisons to siblings are provided.

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

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

Annotations indicate read-only, open-world, idempotent, non-destructive. The description adds that it explicitly reports empty feeds via 'limits[]' and provides an editorial look without inventing products. This is useful behavioral context beyond annotations, clarifying the tool's handling of empty results and honesty constraints.

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 concise (two sentences) and front-loads the main purpose. The empty-feed behavior is placed second. Every sentence contributes, though the wording is slightly abstract. No waste, but could be more concrete.

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 only 3 parameters, adequate schema coverage, output schema exists, and annotations are rich, the description covers key behavior (empty feed handling). However, it lacks specifics on return format, pagination, or how include_products modifies results. Given the tool's moderate complexity, a bit more detail would improve completeness.

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%, with descriptions for query and limit, but include_products lacks a description. The tool description does not add details about parameters beyond what schema already provides, but the schema covers most parameters adequately. The description implicitly hints at query as 'intention', which is already in the schema. No need to compensate significantly, but the missing include_products description leaves a minor 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 it searches for shopping leads based on intent, but it is vague about the exact resource (shopping items) and does not clearly differentiate from sibling tools like 'search' or 'recommend_look'. The verb is implicit ('cherche') and the resource is not explicitly named, leaving ambiguity.

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 explicit guidance on when to use this tool versus alternatives. It mentions handling an empty feed, but does not discuss scenarios like when to prefer recommend_look or search. The context signal of siblings is not leveraged to provide exclusions or 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?

Adds meaningful behavior beyond the annotations: the conditional 's'il y en a' and especially 'même si le feed est vide' disclose that the tool returns a satin article + capsule fallback even with an empty product feed. This is genuine value-add. Consistent with readOnlyHint/idempotentHint; 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?

Two sentences with no filler; the purpose is front-loaded in sentence one. The second sentence, however, is dense internal jargon (article satin, capsule, feed) that could be stated more plainly, slightly hurting accessibility.

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 the safety profile (readOnly, idempotent, non-destructive), the description does not need to explain returns or mutation risk. The main gap is cryptic domain terminology that assumes reader familiarity with Capucine's internal hub/capsule concepts.

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 67% (piece and limit documented, include_products undocumented), placing it in the baseline-3 band. The description adds only marginal parameter insight via the 'Hub chemisier' example; it does not clarify include_products or add syntax detail 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?

States a specific verb (relie/links) with a clear resource: a signature piece to its Capucine look plus verified commercial leads. The 'déjà vérifiées' (already verified) qualifier hints at pre-computed data, which distinguishes it from live search siblings, though no sibling is named explicitly and the jargon ('Hub chemisier', 'capsule') slightly obscures the core 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?

Usage is implied through 'pistes marchandes déjà vérifiées', which suggests this tool uses pre-verified leads rather than live shopping_search. However, there is no explicit when-to-use/when-not-to-use guidance, no named alternatives, and no exclusion criteria given the large 16-tool sibling set.

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 read-only, idempotent, open-world, and non-destructive behavior. The description adds meaningful behavioral context beyond those annotations: the tool depends on local weather and must never assume Paris as a default. 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?

Three short, purposeful clauses: core purpose first, then input constraints, then the no-default-Paris behavior. Every clause earns its place and there is 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?

Given the output schema and annotations, the description sufficiently covers what the tool returns and how to supply location. The main gap is the lack of sibling differentiation, but the core calling requirements are present.

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 documents days, latitude, and longitude, and the description adds semantic value by framing city/postal code OR latitude/longitude as the location selection and confirming that Paris is never assumed. This goes beyond what the schema alone provides.

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 resource: looks for morning, midday, and evening based on local weather. It also specifies location input modes. It doesn't explicitly differentiate itself from the sibling 'recommend_weather_look', so it stops 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?

It gives clear input guidance ('Ville/CP OU latitude+longitude') and an important rule ('Je ne suppose jamais Paris'), but it does not say when to use this tool versus alternatives like recommend_weather_look or get_weather_context. Usage context is implied rather than explicit.

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