Izifete — prestataires événementiels en France

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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds valuable context by stating it returns verified figures from Izifete data, defines the scope (France, event types), and clarifies it outputs numerical benchmarks. This goes beyond the safety annotations and sets correct expectations.

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 well-structured: it opens with the explicit use case, lists example topics, states the output source, and ends with clear exclusions. Every sentence contributes essential information without redundancy, and the length is justified by the need for 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?

Given a simple single-parameter tool with strong annotations and no output schema, the description is complete. It covers input expectations, output type, domain scope, and exclusions, providing sufficient context for an agent to invoke it correctly and understand what to expect.

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 'question' is already thoroughly described in the schema with examples. The description does not add extra semantic detail about the parameter's format or constraints, so the baseline of 3 is appropriate since the schema carries the full burden.

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 advice and budget estimates for organizing events in France, with specific resource types (weddings, birthdays, etc.) and topics (budget, quantities, timing, provider selection). It explicitly distinguishes from sibling tools like search and conseils_prestataire, making its purpose 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?

It provides explicit when-to-use guidance (when user is organizing an event in France and asking for advice) and when-not-to-use guidance (not for finding specific providers, not for professionals), naming the alternative tools. This fully covers decision-making criteria.

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

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

Annotations already declare the tool as readOnly, idempotent, and non-destructive. The description adds beyond annotations by stating the advice is 'conseils concrets issus des données et guides Izifete.' It does not contradict annotations and provides some context about the output source and nature, though it could mention limitations (e.g., no legal guarantee). Overall, it adds value beyond the structured metadata.

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, front-loaded with the core purpose and usage condition. Every sentence serves a purpose: defining the audience, listing example topics, stating the output source, and providing exclusions with alternative tools. No redundancy or 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?

The tool is simple (one parameter, no output schema), and the description fully covers it: when to use, what it does, what it returns, and when not to use. It includes targets audience, example queries, and exclusions. No missing critical context 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?

The schema already covers the single parameter 'question' with a clear description and min/max lengths. The tool description adds value by providing specific example questions and reiterating the expected domain. This extra context helps the agent formulate valid queries, going beyond the schema's generic description.

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

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

The description clearly identifies the tool's purpose: providing business advice to French event industry professionals (DJ, caterer, photographer, etc.). It specifies the exact audience (PROFESSIONNEL de l'événementiel) and the type of queries (finding clients, pricing, legal obligations). This clearly distinguishes it from sibling tools like conseils_evenement, which serves individuals.

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

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

The description explicitly states when to use the tool ('Utilise cet outil quand l'utilisateur est un PROFESSIONNEL...') and lists concrete example questions. It also explicitly says when NOT to use it, naming the alternative tool (conseils_evenement) and other excluded cases (creating a profile or request). This is exemplary 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?

Beyond annotations (readOnlyHint=false, destructiveHint=false), the description discloses account/login requirements, the verification email usage, that the request is reviewed by the Izifete team before transmission, and that no payment data is collected. This adds valuable behavioral context not present in 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 moderately long but well-structured and front-loaded with the critical prerequisite. Each sentence serves a purpose (prerequisite, action, review process, confirmation, exclusions). Minor redundancy exists, but it remains concise for the complexity.

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 prerequisites, creation workflow, review process, exclusions, and account requirements. It does not explicitly state what the function returns after a successful call, but the absence of an output schema and the described handoff to Izifete provide sufficient context for most scenarios.

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 every parameter described. The description mentions some fields (event type, city, date, budget, message) in passing but adds no further parameter-level meaning beyond the schema. 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 clearly states the tool creates a targeted quote request ('Crée une demande ciblée') and distinguishes it from sibling tools by explicitly excluding search, fetch, and verifier_entreprise. The verb+resource combination is specific and 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 provides explicit usage conditions: use only after the user has selected a provider and confirmed, always ask for confirmation before calling, and lists what the tool is NOT for (search, fetch, verifier_entreprise). This is exemplary 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 already declare readOnly, idempotent, and non-destructive behavior, so the bar is lower. The description adds value by specifying the return content ('Renvoie ses métiers, sa ville, sa note, sa description et le lien de sa fiche izifete.fr') and the prerequisite that the ID must come from a prior search. No contradictions 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 concise, using three sentences that each serve a purpose: when to use, what it returns, and exclusions. It is front-loaded with the main usage directive and contains no filler or unnecessary details.

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

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

Given the tool's simplicity (1 parameter, no output schema), the description is complete: it explains the input source, return fields, and exclusions, and is aligned with annotations. There are no significant gaps for an agent to misuse this 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?

The schema already fully describes the only parameter 'id' with the description 'Identifiant du prestataire renvoyé par search' (100% coverage). The tool description repeats this same information ('à partir de son identifiant obtenu via search'), adding no new meaning beyond the schema, 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?

The description clearly states that this tool fetches details of a specific Izifete provider using an ID from search: 'Utilise cet outil quand l'utilisateur veut les détails d'un prestataire Izifete précis, à partir de son identifiant obtenu via search.' It explicitly distinguishes itself from sibling tools by excluding search (search) and request creation (creer_demande).

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 explicit when-to-use guidance ('quand l'utilisateur veut les détails d'un prestataire précis') and when-not-to-use guidance ('N'utilise PAS cet outil pour rechercher plusieurs prestataires (search) ni pour envoyer une demande (creer_demande)'), clearly differentiating from 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 read-only, idempotent, non-destructive. The description adds context beyond annotations: returns city, distance, rating, link, and scope limitations. No contradiction; useful behavioral detail.

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 serving a purpose: trigger, return contents, and exclusions. Slightly long but well-structured with 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?

No output schema, so the description carries the responsibility of explaining returns. It lists output fields, geographic scope, and tool exclusions, making it complete for a single-param search 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 has 100% coverage of the single 'query' parameter with a clear example. The description reinforces 'par métier et par ville' but adds no new technical syntax 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 verb ('cherche un prestataire') and resource ('prestataires vérifiés') with clear scope (France/Monaco, event types, professions). It explicitly differentiates from sibling tools by naming exclusions (verifier_entreprise, fetch, creer_demande).

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?

Opening phrase 'Utilise cet outil quand...' gives explicit conditions. Negative guidance ('N'utilise PAS') names alternative tools, covering both when-to-use and when-not-to-use.

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, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description reinforces 'Aucune donnée n'est modifiée' and adds concrete context: the data source (recherche-entreprises.api.gouv.fr), the geographic scope (France), and the fact that it returns official public data. This goes beyond the annotations.

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

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

The description is efficiently written with each sentence contributing meaningful guidance: when to use, what it returns, safety confirmation, and exclusion. It is front-loaded with the purpose and avoids unnecessary detail.

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 rich annotations and no output schema, the description fully covers the necessary context: purpose, data source, return content, non-destructive behavior, non-usage cases, and geographic scope. The agent has all needed information to select and invoke the tool correctly.

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

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

The schema provides 100% coverage for the single parameter 'siret', including pattern, length constraints, and a clear description of allowed SIRET/SIREN formats. The tool description adds no extra parameter syntax or semantics beyond what the schema already documents, so a baseline score of 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 clearly states the tool's purpose: verifying the reliability of a French company using a SIRET/SIREN number via official public data. It specifies the return fields (raison sociale, adresse, statut) and explicitly distinguishes from the search tool used for finding providers.

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 explicit when-to-use guidance: 'Utilise cet outil quand l'utilisateur veut vérifier la fiabilité d'une entreprise française' and provides a clear exclusion: 'N'utilise PAS cet outil pour rechercher des prestataires (search).' This directly addresses alternatives among siblings.

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