eyeot ERP

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

Annotations are all false, so the description must convey behavioral traits. It states a state change (marking as accepted) but does not disclose side effects, reversibility, or response format.

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 phrase with no wasted words. Efficiently communicates the core purpose.

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

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

For a simple tool with one parameter and no output schema, the description is functionally adequate but lacks behavioral and usage context, making it only moderately 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 coverage is 100% with one parameter (quote_id described as 'path parameter'). The description adds no additional meaning beyond the schema, but the parameter is self-explanatory.

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 action ('marquer un devis accepté') and the resource (quote). It distinguishes from sibling tools like 'create_quote' (creates a new quote) and 'convert_opportunity_to_quote' (converts opportunity to quote).

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 guidance on when to use this tool versus alternatives, no prerequisites (e.g., quote must exist, not already accepted), and no when-not-to-use context 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 are present but only state readOnlyHint=false and destructiveHint=false. The description does not disclose whether the original opportunity is modified, if a new quote is created, or any side effects. This is insufficient for a mutation operation.

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 short sentence with no fluff. However, it sacrifices necessary detail for brevity, resulting in an inadequate explanation.

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 moderate complexity (one required parameter, no output schema), the description should explain key behaviors like whether the opportunity is converted in-place or a new quote is created. The current French description lacks this context, making it incomplete for an English-speaking AI 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% for the single parameter 'opportunity_id', but the description adds no extra meaning; the schema description '(path parameter)' is minimal. The tool description does not clarify the parameter's role or format.

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 'Convertir une opportunité en devis' clearly states the action (convert) and the resources (opportunity to quote). It distinguishes from sibling tools like create_quote and invoice_from_quote. However, it could be more specific about what the conversion entails.

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 guidance on when to use this tool versus alternatives such as create_quote or invoice_from_quote. The agent is left to infer the 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?

Description does not add any behavioral context beyond what annotations provide. Annotations show readOnlyHint=false and destructiveHint=false, so it's a write operation. The description should clarify what happens on creation (e.g., duplicate handling, required fields) but fails to do so.

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 (2 words). While it lacks detail, it is not verbose. A slightly longer description would improve clarity, but for a simple purpose, it is not overly wasteful.

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 complexity of the input schema (many optional fields) and no output schema, the description should explain the creation behavior, validation rules, or success criteria. It does none of these, leaving the agent underinformed for a nontrivial operation.

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 clear property definitions (types, patterns, enums). The description adds no additional meaning to the parameters, but the schema itself is comprehensive. 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 is 'Créer un client' which clearly states the action (create) and resource (client). The name itself also conveys this, so it is clear but does not differentiate from siblings like 'update_client' or 'get_client', which are distinct by their verb.

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 guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, when not to use it, or any contextual cues that help the agent decide between creating a client and other similar actions like creating an opportunity or employee.

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 all false, offering no safety or behavioral hints. The description does not disclose any behavioral traits (e.g., required permissions, side effects, or return behavior). With no annotations to lean on, the description should carry the burden but fails to do so.

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 short (two words in French), but it is underspecified rather than concise. It lacks critical information and does not earn its place as it provides no value beyond the name.

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

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

Given the absence of input schema parameters, output schema, and annotations, the description is critically incomplete. It does not explain how to create an employee, what happens upon success, or any preconditions. The tool is unusable based on this definition alone.

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 no parameters (empty object) and schema description coverage is trivially 100%. Baseline for parameter semantics is 3 when coverage is high, but the description adds no extra meaning about parameters (e.g., that none are needed or that the schema is likely incomplete). It neither helps nor harms, hence a baseline score.

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 'Créer un employé' is French for 'Create an employee', which is essentially a translation of the tool name. While it identifies the resource, it adds no additional context and is essentially a tautology (repeating the name in another language). Among sibling 'create_*' tools, it distinguishes by resource but provides no scope or detail.

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 usage guidance is provided. The description does not specify when to use this tool versus alternatives like create_client or create_invoice, nor does it mention prerequisites or context. The agent receives no help in deciding which tool to invoke.

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 a mutating tool (readOnlyHint=false) but provide no further behavioral details. The description does not explain what happens when creating an invoice with no parameters—e.g., whether it creates a blank draft, uses context, or errors out.

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 phrase. It is to the point, though it could benefit from a brief usage note.

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 parameters and no output schema, the description should clarify the tool's behavior (e.g., what invoice is created). It lacks completeness for a tool that presumably requires some implicit input.

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% coverage, so the description does not need to add parameter info. However, the absence of parameters is unusual for a create tool, and no explanation is given.

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 'Créer une facture' clearly translates to 'Create an invoice', specifying the verb and resource. However, it does not distinguish this tool from the sibling 'invoice_from_quote', which also creates an invoice but from a quote.

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 guidance is provided on when to use this tool versus alternatives like 'invoice_from_quote'. The description lacks context about prerequisites or typical usage scenarios.

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 does not disclose behavioral traits such as whether the tool returns the created resource's ID, whether it requires specific permissions, or what side effects occur. Annotations are all false, leaving the agent with no additional insight.

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?

While very concise (one phrase), the description is under-specified. It sacrifices usefulness for brevity and does not earn its place as a net improvement over the tool name.

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

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

Given the lack of output schema and annotations, the description is incomplete. It fails to explain what happens on success (e.g., returns opportunity ID) or any operational constraints.

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 covers all parameters with constraints and descriptions for the body object, so schema coverage is high. However, the description adds no further meaning beyond what the schema 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 'Créer une opportunité' is a tautology of the tool name. It states the tool creates an opportunity but provides no detail to distinguish it from sibling tools like create_quote or create_order.

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 guidance on when to use this tool versus alternatives. There are many sibling tools for creating CRM entities, but the description offers no context for selection.

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 all annotations false, the description must disclose behavioral traits, but it only states the action. No information on side effects, required permissions, or safety is given.

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 very concise (one short sentence), but it lacks key information needed for a tool with nested parameters. It earns points for brevity but loses for under-specification.

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 nested input schema and no output schema, the description is severely incomplete. It fails to clarify required fields, order flow, or return values.

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 description adds no meaning beyond the schema; it does not explain parameters like items, supplier_id, or expected_delivery_date. Inner property descriptions are absent in schema, and description does not compensate.

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 'Créer un bon de commande' clearly states the verb (Créer) and resource (bon de commande, i.e., purchase order), distinguishing it from sibling create tools like create_invoice or create_quote.

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 on when to use this tool versus alternatives, nor any prerequisites or context for usage.

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 does not add behavioral context beyond the name 'create product'. Annotations indicate mutation (readOnlyHint=false) but no other traits like idempotency or error behavior are disclosed. Additional context such as duplicate handling or required permissions would improve 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 short (one phrase) but lacks necessary detail. Conciseness is not valuable when it omits critical information; this is under-specification, not efficient communication.

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 complexity of the nested input schema (17+ fields) and no output schema, the description is completely inadequate. It fails to explain return values, validation rules, or any side effects, leaving an agent poorly equipped to use 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?

Despite the input schema having many nested properties with no descriptions, the tool description provides no explanation of any parameter. The schema description coverage is effectively low because only the top-level 'body' has a description. The agent is left without guidance on what each field means.

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 the verb 'Créer' (create) and resource 'produit' (product), which is clear enough. However, it does not differentiate from sibling tools like create_client or create_invoice, and the phrase '(catalogue stock)' is ambiguous.

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 guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, constraints, or context that would help an agent decide to use this over other create 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?

While annotations exist (e.g., readOnlyHint=false), the description does not add any behavioral context such as authentication requirements, side effects, or response behavior. Annotations alone are insufficient for complex operations.

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 short (3 words), but it is under-specified and fails to provide necessary information. It is not concise in a helpful way—it sacrifices completeness for 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?

Given the tool's complexity (nested objects, multiple required fields) and lack of output schema, the description should explain what a quote represents and how it differs from similar entities like invoices. The current description is incomplete for effective 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 covers all parameters with 100% description coverage for the top-level 'body'. However, the description adds no meaning beyond what the schema provides, and nested properties lack descriptions. Baseline 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 'Créer un devis' is a direct French translation of the tool name, adding no additional detail or differentiation from sibling tools like 'accept_quote' or 'convert_opportunity_to_quote'. It is essentially a tautology, failing to specify scope or unique behavior.

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 guidance is provided on when to use this tool versus alternatives. There is no mention of use cases, preconditions, or when not to use it.

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?

All annotations are false, so the description carries full responsibility for behavioral disclosure. It only provides the action 'create' without any details on side effects, permissions, or return values. The description is insufficient for a mutation 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?

The description is extremely concise but lacks necessary detail. While front-loaded, it is too short to be informative, making it under-specified rather than efficiently concise.

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 tool with a complex nested schema and no output schema, the description fails to provide any contextual information about what a ticket is, how the body is used, or expected outcomes. It is not complete enough.

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 a description for the 'body' parameter. However, the description adds no meaning beyond the schema's 'Request body' label. Baseline 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 'Créer un ticket IT' clearly states the action (create) and object (IT ticket), but does not differentiate from sibling tools like create_client or create_invoice. The verb and resource are specific enough for basic understanding.

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 guidance on when to use this tool versus alternatives, such as create_order or create_invoice. No prerequisites or context 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 already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds no behavioral context beyond stating it provides alerts, such as confirmation of no side effects or what happens on execution. With annotations present, the description does not contradict them but adds negligible value.

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 short phrase, which is concise but lacks substance. It could be more informative without becoming verbose. It is not tautological but barely adds anything beyond the name.

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

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

Given the lack of output schema and no parameter details, the description should at least hint at what the alerts contain (e.g., count, severity, recent alerts). It is incomplete for an agent to understand what to expect from the 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 input schema has no parameters with 100% coverage. The description could explicitly state that no parameters are required, but it is not necessary since the schema is empty. Baseline for zero parameters is 4.

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 'Alertes du dashboard' and the tool name together clearly indicate the tool provides dashboard alerts, but it lacks specificity about what kind of alerts or how they are presented. It does not distinguish from sibling tools like dashboard_kpis or stock_dashboard.

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 guidance is provided on when to use this tool versus alternatives such as dashboard_kpis or stock_dashboard. The description does not mention any context, prerequisites, or exclusions.

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 domain context ('KPIs du dashboard principal') but does not elaborate on behavioral traits beyond what annotations provide.

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: one short sentence that contains all necessary information. 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?

While the description is adequate for a simple tool with no parameters, it could be more informative by specifying what KPIs are returned or the format. Without an output schema, some detail 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?

No parameters exist, so baseline score is 4. The description does not need to explain parameters because schema coverage is 100% and there are none.

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 'KPIs du dashboard principal' clearly states it returns KPIs for the main dashboard. It distinguishes from sibling tools like 'dashboard_alerts', which likely returns alerts rather than KPIs.

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. However, the tool has no parameters and a self-evident purpose, so minimal guidance is needed.

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 destructive hint, and description adds parameter routing behavior and the prerequisite, providing useful context beyond 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?

Four concise sentences: purpose, format example, prerequisite, parameter behavior. No fluff, 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?

No output schema, but description covers purpose, parameters, and usage context adequately for a generic execution 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 description coverage is 100%; description adds value by clarifying the canonical name format and that params contains mixed parameters, slightly beyond 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?

Clarifies the tool executes an eyeot ERP action by canonical name with format examples, distinguishing from sibling tools (specific CRUD actions).

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 instructs to use eyeot_help first, providing prerequisite guidance, though does not explicitly state when to avoid using it (e.g., when a specific tool exists).

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 indicate readOnly, idempotent, non-destructive. The description adds value by specifying output details per parameter (e.g., 'retourne le détail (path, méthode, params, schema body)'), but 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?

The description is concise and well-structured: front-loaded with purpose, then each usage case in separate sentences. No unnecessary 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 catalog tool with 3 optional params and no output schema, the description fully explains the return values for each invocation mode, covering all necessary context for an agent to use it effectively.

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 descriptions. The description enriches semantics with examples and format clarifications (e.g., action='rh.employes.create') and explains the output for each param combination.

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: 'Catalog des actions disponibles sur eyeot ERP'. It details specific behaviors for different argument combinations (no args, module, action, search), making it distinct from siblings like eyeot_call.

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 eyeot_help before eyeot_call ('Toujours appeler eyeot_help AVANT eyeot_call') and explains when to use each parameter (module, action, search) with 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 description adds no additional behavioral context. It does not mention response format, error conditions, or any other behavioral traits.

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 zero wasted words. It efficiently conveys the core purpose.

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

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

For a simple read-only tool with one parameter, the description is sufficient to understand basic functionality. However, it lacks mention of return format or error handling, which would be helpful but not critical given the tool's 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% with the single parameter client_id described as '(path parameter)'. The description reinforces that the id is used for retrieval but adds minimal new meaning 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 'Récupérer un client par id' clearly states the action (retrieve), resource (client), and method (by id). It distinguishes from siblings like list_clients (retrieve all) and update_client (modify).

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 on when to use this tool versus alternatives like search or list. No when-to-use or when-not-to-use information is included.

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 all false, providing no safety hints. The description only states 'create' without disclosing side effects, permissions needed, or idempotency. As a mutation tool, it should offer more behavioral context.

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 short sentence with no unnecessary words. It is concise, but could benefit from additional details without being verbose.

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 lack of output schema and minimal annotations, the description is insufficient. It does not explain what happens if the quote is already invoiced, whether the quote must be in a certain state, or what the created invoice contains.

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%, but the description adds no meaning beyond the schema. The parameter 'quote_id' is only described as '(path parameter)' in the schema, and the tool description does not clarify its format or expected values. Baseline of 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's function: 'Créer une facture à partir d'un devis' (Create an invoice from a quote). This specific verb+resource combination distinguishes it from siblings like create_invoice and accept_quote.

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 guidance on when to use this tool versus alternatives (e.g., create_invoice, accept_quote). The description does not mention prerequisites, status requirements, or when not to use it.

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 description's addition of '(CRM)' is minimal. No further behavioral traits (e.g., default ordering, pagination) are disclosed, but the annotations cover safety.

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

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

The description is a single, concise phrase that is front-loaded. It contains no unnecessary words, but could benefit from slight expansion to improve clarity.

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 no parameters, no output schema, and comprehensive annotations, the description is minimally complete for a simple list operation. It does not specify return format or ordering, but that is acceptable for a basic 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?

No parameters exist, so the description adds nothing beyond the schema, which is 100% covered. Baseline for 0 parameters is 4, and no additional parameter info is needed.

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 'Lister les clients (CRM)' clearly states the action (list) and resource (clients), specifying the CRM domain. This distinguishes it from sibling tools like get_client (single client) and create_client, but does not differentiate from other list_* 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?

No guidance on when to use this tool versus alternatives like get_client or search. It lacks context for optimal usage, such as explaining that it returns a list of all clients without filtering.

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 indicate readOnlyHint=true and idempotentHint=true, but the description adds no behavioral context beyond that (e.g., return format, pagination, ordering). It offers zero additional 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?

Description is a single, direct phrase that earns its place by stating the purpose without any waste. It is appropriately sized and front-loaded for a simple tool.

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 good annotations and no parameters, the description omits important context such as what fields are returned, whether the list is comprehensive or filtered, or any pagination behavior. Without an output schema, this lack of detail leaves the agent underinformed.

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 no parameters, and the input schema covers this completely (100% coverage). Per guidelines, with 0 parameters the baseline is 4; the description does not need to add parameter information.

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

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

Description 'Lister les employés' clearly states the verb 'list' and the resource 'employees', directly conveying the tool's purpose and distinguishing it from sibling tools like list_clients or list_invoices.

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

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

Description provides no guidance on when to use this tool versus alternatives such as search or other list tools. No context on prerequisites, filtering, or scope is given.

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, destructiveHint=false, idempotentHint=true, so the description need not repeat them. It adds no additional 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?

Extremely concise single sentence that is front-loaded with the key action and resource. No unnecessary 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?

Adequate for a simple zero-parameter list tool with thorough annotations, but no explanation of return format or pagination. Minimal but functional.

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?

No parameters exist, and schema coverage is 100%. Description adds no parameter-level meaning, but the baseline of 3 applies given high coverage.

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

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

The description 'Lister les factures' clearly states the verb (list) and resource (invoices), directly distinguishing it from sibling tools like 'create_invoice' or 'list_quotes'.

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 guidance on when to use this tool vs alternatives. Does not indicate prerequisites or when not to use it.

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 and idempotentHint. Description adds no extra behavioral info beyond the verb, but 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?

Single short phrase, front-loaded and clear. No wasted words, though slightly more structure (e.g., scope) could help.

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 and no details about what leave requests are listed (all, pending, etc.). Leaves many questions for the 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?

Has zero parameters, so schema coverage is 100%. Description adds no param-specific info, but baseline for 0 params is 4.

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 'List leave requests' (French), which is a specific verb+resource. It distinguishes from sibling 'request_leave' which is for creating leave requests.

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 guidance on when to use this tool vs alternatives (e.g., list_employees). No context about scope 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, fully covering safety and idempotency. The description adds no further behavioral context (e.g., pagination, filtering, or result scope). With annotations covering the core traits, a score of 3 is appropriate.

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, short sentence with no extraneous words. It is maximally concise for the information it conveys.

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 no output schema and simple zeroparameter input, the description is minimally complete. However, it fails to specify what the output contains, any ordering, or scope of the list. For a basic tool, it suffices but lacks detail that would help an agent anticipate the result.

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, so schema description coverage is effectively 100%. The description adds no parameter information, but none is needed. Baseline 3 is applied.

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 'Lister les opportunités commerciales' clearly indicates the tool lists commercial opportunities. It uses a specific verb+resource pattern. However, it does not differentiate from sibling list_* tools like list_clients or list_invoices, which weakens clarity for agent selection.

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 on when to use this tool versus alternatives such as create_opportunity, convert_opportunity_to_quote, or sibling list tools. No context for prerequisites or exclusions is given.

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, which cover the safety profile. The description adds no additional behavioral context (e.g., pagination, sorting, or authentication requirements), but 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?

The description is a single concise sentence, efficiently conveying the core purpose. However, it could be slightly more informative without losing conciseness, e.g., mentioning the output scope.

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 defined, the description should provide some indication of what data is returned (e.g., order IDs, dates, statuses). The current description is too minimal to fully inform the AI agent about the tool's behavior.

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, and schema coverage is 100%. The description does not add parameter details, which is acceptable given zero parameters. However, it could hint at the output schema to compensate for missing output 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 clearly states the action (list) and the resource (orders, specifically 'bons de commande' meaning purchase orders). It distinguishes this tool from sibling list tools like list_clients or list_quotes by specifying the exact record type.

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 guidance is provided on when to use this tool vs alternatives like list_quotes or list_invoices. The description is too brief to imply any usage context or exclusions.

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, destructiveHint=false. Description adds no behavioral information beyond stating it lists products, which is consistent with annotations. With annotations carrying the burden, this is adequate.

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

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

Extremely concise single phrase with no wasted words. Front-loaded with purpose. Appropriate for a simple parameterless tool.

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 no output schema and no parameters, the description is minimal but functional. It could mention that it lists all products (or perhaps not) and any default behavior. Adequate but leaves room for improvement.

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?

Zero parameters with 100% schema coverage. Description adds no parameter info, but baseline is 4 as schema fully addresses parameters. No additional context needed.

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 'Lister les produits / catalogue' clearly indicates the tool lists products, using a specific verb ('List') and resource ('products'). It differentiates from sibling tools by naming the resource, but could be more explicit.

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 guidance on when to use this tool versus alternatives like search or other list tools. The description lacks context for selection among many sibling list 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows this is a safe read operation. The description adds no further behavioral details but 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?

The description is extremely concise (3 words) with no superfluous content. It front-loads the purpose effectively, though it could be slightly more informative.

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

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

Given the simple list operation, no parameters, and rich annotations, the description is minimally adequate. However, it does not specify scope (e.g., all quotes or filtered) or return format, which could be improved.

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 no parameters, so the description bears minimal burden. It does not add any context about what the list returns, but baseline 3 is appropriate per the scoring rules.

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 'Lister les devis' clearly specifies the verb 'list' and the resource 'quotes', distinguishing it from sibling tools like list_invoices or list_orders. However, the French language may reduce clarity for non-French agents.

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 guidance is provided on when to use this tool over alternatives such as list_orders or list_invoices. The description lacks context about use cases or exclusions.

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, indicating a safe read operation. The description adds no additional behavioral context beyond the tool name, such as side effects, permission requirements, or rate 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?

The description is extremely concise—two words in French—with no unnecessary information. It is front-loaded and efficient, though slightly minimal for full clarity.

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 no parameters, a full output schema is absent, and annotations cover safety, the description provides the core purpose. However, it lacks any detail about the output format, such as fields returned or pagination, which would be needed for an agent to fully understand the response.

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

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

The tool has zero parameters, so the input schema provides no meaning. The description adds value by specifying the tool's purpose (listing low stock alerts). For a parameterless tool, this is adequate, though it does not describe the output structure.

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 'Alertes stock bas / rupture' clearly states the tool lists low stock or stockout alerts, specifying both the verb (list) and resource (stock alerts). It distinguishes itself from sibling tools like 'dashboard_alerts' and 'stock_dashboard' by focusing specifically on stock alerts.

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 viewing low stock alerts but offers no explicit guidance on when to use this tool versus alternatives such as 'stock_dashboard' or 'dashboard_alerts'. No exclusions or prerequisites are mentioned.

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, destructiveHint=false. The description adds no additional behavioral context, such as safety, idempotency, or any 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 extremely concise (one phrase) and front-loaded with the purpose. However, it may be too brief to be fully helpful, but it achieves the minimum without waste.

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 simplicity (no parameters, no output schema), the description still lacks contextual completeness. It does not mention what the output contains, sorting, pagination, or any selection criteria. With a short description and no output schema, the agent may be left guessing.

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. According to guidelines, 0 parameters warrants a baseline of 4. The description does not need to add parameter info.

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 action ('Lister') and resource ('fournisseurs'), which translates to 'list suppliers'. It is specific and distinguishes from sibling tools like list_clients, list_employees, etc.

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 guidance is provided on when to use this tool versus alternatives. There is no mention of when-not to use or any differentiation from other list_* 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?

Annotations indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false, which imply safe, read-only behavior. However, the description adds no behavioral context beyond these annotations, such as pagination, filtering, or return structure. Given the annotations already cover safety, the description provides no additional value.

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 short (one phrase), which is concise but under-specified. It lacks any structure or additional information, making it minimally viable but not well-formed.

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 annotations covering safety, the description fails to mention what the tool returns (e.g., a list of tickets) or any other context. For a list tool, this is insufficient for complete understanding.

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 zero parameters and schema coverage is 100% (trivially). Per the guidelines, a baseline score of 4 applies when there are no parameters. No parameter documentation is needed.

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 'Lister les tickets IT' specifies the verb 'list' and the resource 'tickets IT', which is clear and distinguishes from sibling list tools for other entities. However, it is essentially a translation of the tool name and does not add extra specificity.

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 usage guidance is provided. The description does not indicate when to use this tool over alternatives like search or other list tools, nor does it mention any prerequisites or 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=true, idempotentHint=true, and destructiveHint=false, covering safety traits. The description 'Récupérer le PDF' is consistent with a read operation and adds no extra behavioral context (e.g., error handling, return format). It meets the minimum bar without 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?

The description is a single, front-loaded sentence with no extraneous words. It efficiently communicates the tool's purpose.

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

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

For a simple retrieval tool with one parameter and no output schema, the description is mostly complete. It does not specify the return format (e.g., binary PDF, URL), but 'Récupérer le PDF' sufficiently implies the output. Slightly enhanced completeness would be ideal.

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 one required parameter 'quote_id' described as '(path parameter)'. The description does not add semantic meaning beyond the schema; it only implies that the parameter identifies the quote. Baseline 3 is appropriate since the schema covers all parameters.

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

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

The description 'Récupérer le PDF d'un devis' clearly states the action (retrieve) and resource (PDF of a quote). It distinguishes from sibling tools like accept_quote, create_quote, and list_quotes, which handle different operations on quotes.

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?

Although no explicit when/when-not guidance is given, the tool's name and description provide clear context: use this tool when you need the PDF of a specific quote. The sibling list includes no other PDF retrieval tool, so there is no ambiguity.

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 the tool is not read-only, not idempotent, and not destructive, but the description adds no behavioral context beyond what annotations already provide. It does not explain that requesting leave typically triggers an approval workflow, nor does it mention any side effects or permissions needed.

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 very short (one sentence in French), which is concise but overly minimal. It lacks structure and front-loading of important details. While there is no wasted text, the brevity sacrifices usefulness.

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 there is no output schema and the tool has six nested parameters, the description is incomplete. It does not explain what happens after a successful request (e.g., pending approval, calendar blocked), nor does it clarify required versus optional fields. The description fails to fully equip an AI agent to use 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 input schema has 100% coverage at the top level (the 'body' parameter has a description), but the nested parameters like 'type', 'reason', and 'half_day_start' have no descriptions. The tool description does not add any meaning beyond the schema; it could have explained the date format or the meaning of half-day booleans but does 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 'Demander un congé' clearly indicates the action (request) and resource (leave). It is a specific verb+resource pair that distinguishes it from sibling tools like 'list_leaves' (read). However, it does not explicitly differentiate from other leave-related tools that might exist.

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 information about when to use this tool versus alternatives. It lacks any context about prerequisites, such as employee login or available leave types, and does not mention when not to use it.

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 indicate readOnly, idempotent, destructive=false. The description adds 'global cross-module' but no additional behavioral context beyond 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?

Extremely concise (single phrase), but at the cost of missing essential details about usage. Could benefit from expanding slightly without becoming verbose.

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?

Lacks crucial information: how to input search query, what modules are searched, what results look like. The absence of an output schema makes this gap worse.

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 no parameters, but the description implies a search query is needed. Without explaining how the query is provided (e.g., via prompt), the meaning is unclear.

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 'global cross-module search,' which is clear but vague. It doesn't specify which modules or what kind of data is searched.

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 guidance on when to use this tool versus the many list tools (e.g., list_clients). The description should mention it's a unified search alternative.

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 and idempotentHint=true, indicating safe read behavior. The description adds no additional behavioral context beyond the tool's name, but 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?

The description is extremely concise at 3 words, which is efficient but may be too sparse. It is front-loaded but lacks meaningful 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?

Given zero parameters and simple read-only nature, the description is minimally adequate but does not explain what KPIs are displayed or how this differs from sibling tools like 'dashboard_kpis'.

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, and schema description coverage is 100% (vacuous). The description does not need to add parameter details.

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 'Dashboard stock (KPIs)' is vague and does not clearly state what the tool does. It is not a verb+resource pair and does not distinguish itself from sibling tools like 'dashboard_kpis'.

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 guidance is provided on when to use this tool versus alternatives such as 'dashboard_kpis' or 'list_stock_alerts'. The description lacks context for appropriate 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 are minimal (no hints). The description adds no behavioral context, such as whether updates are partial, idempotent, or require specific permissions.

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 very short (one sentence), but it is too minimal and does not add value. It is concise but under-specified.

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 complexity of the input schema (many fields) and absence of output schema, the description should mention return behavior or confirmation. It does not, leaving the agent uninformed about the update result.

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 description does not need to add parameter details. However, it provides no additional semantics 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 'Mettre à jour un client' is a tautology, restating the tool name without adding clarity. It does not differentiate this tool from siblings like create_client or get_client.

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 guidance on when to use this tool versus alternatives such as create_client or get_client. No context on prerequisites or limitations.

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 indicate read-only, idempotent, non-destructive behavior. The description adds specific information about what is retrieved (user, org, permissions) but does not elaborate on structural 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 purpose and crucial usage instruction. Every word adds value with no 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 no parameters and robust annotations, the description is complete for its purpose. It provides purpose and usage context, though it could hint at output 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?

No parameters exist, and schema coverage is 100%. Baseline score of 4 applies, as the description does not need to explain parameters.

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

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

The description clearly states the tool returns the authenticated user, active organization, and permissions. It distinguishes itself from sibling tools like create_client or list_clients by focusing on the current session context.

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 this tool 'before any response mentioning org/user/plan/role', providing clear context for use. It does not mention alternatives, but its unique purpose makes this sufficient.

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