eyeot ERP

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

Annotations already indicate non-readOnly and non-idempotent behavior. The description adds no additional behavioral context such as side effects, permissions, or irreversible changes, providing little value 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 a single sentence, very concise with no wasted words. However, it could be slightly more detailed 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?

Given a simple tool with one parameter and no output schema, the description lacks workflow context. It does not mention what happens after acceptance (e.g., status change, invoicing), which is critical for an agent to understand the tool's role in a broader process.

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

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

With 100% schema description coverage (the only parameter 'quote_id' is described as a path parameter), the description does not add further meaning. 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 'Marquer un devis accepté (par le client)' clearly states the action (mark accepted) and the resource (quote). It is specific and distinguishable from sibling tools like 'create_quote' or 'convert_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 or when not to use this tool, nor any mention of alternatives or preconditions. The usage is implied but not explicit.

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 it is not read-only or destructive, but the description does not disclose behavioral traits, such as whether it creates a new quote, marks the opportunity as converted, or requires specific permissions. Beyond annotations, it adds no 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 sentence, which is concise and front-loaded. However, given the lack of other details, it may be too minimal for a complete understanding.

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

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

With only one parameter and no output schema, the description should still explain the conversion behavior and result. Currently, it lacks details on what the tool returns or any side effects, leaving 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?

Schema coverage is 100% for the single parameter, so the description does not need to add much. However, it provides no additional semantic context about the opportunity_id format or any constraints beyond the schema's 'path parameter' note.

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 resources (opportunity to quote). It distinguishes from sibling tools like create_opportunity, create_quote, and accept_quote by specifying a conversion operation.

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 offers no guidance on when to use this tool versus alternatives such as create_quote or accept_quote. There are no usage contexts or exclusions 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 all false and the description adds no behavioral details. There is no mention of side effects, authentication needs, or what happens on duplicate creation. The description does not contradict annotations, but it fails to compensate for the absence of behavioral hints.

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), which is concise but comes at the expense of providing necessary context. It is not structured and omits critical information.

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

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

Given the tool's complexity (multiple nested fields, no output schema, no annotations), the description is woefully incomplete. It fails to explain return values, required fields, or expected behavior, leaving the agent with insufficient context 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?

Although schema description coverage is 100% (only the 'body' parameter has a description), the nested fields (city, name, etc.) lack descriptions in both the schema and the tool description. The description adds no semantic value beyond the schema, leaving the agent to infer meaning from property names alone.

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 client' is a tautology of the tool name 'create_client'. It does not specify the resource type (client vs. other entities) or distinguish it from sibling tools like update_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 is provided on when to use this tool versus alternatives such as create_opportunity or convert_opportunity_to_quote. The description lacks prerequisites, exclusions, or context for 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?

The description does not disclose behavioral traits beyond the annotations, which are all false. With no annotations providing safety or idempotency cues, the description carries the burden but adds nothing about side effects, permissions, or response behavior.

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 brief (one sentence) but is under-specified rather than concise. It fails to provide useful information that earns its place, repeating the tool's name in French.

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 (no parameters, no output schema), the description is still incomplete. It does not explain what creating an employee entails, potential constraints, or follow-up actions, leaving the agent with no context for safe usage.

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 is empty with 100% coverage, so baseline is 3. The description does not add any parameter information beyond the schema, but since no parameters exist, no additional semantics are 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 'Créer un employé' is a French translation of the tool name, providing minimal additional meaning. It states the verb (create) and resource (employee) but does not differentiate from sibling create tools like create_client or create_invoice.

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 create_client or create_invoice. The description lacks context for prerequisite conditions or scenarios where this tool is appropriate.

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

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

No annotations are set, and the description fails to disclose any behavioral traits such as side effects, authorization requirements, idempotency, or return values. The tool presumably creates an invoice, but the description offers no transparency beyond that.

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

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

The description is extremely short (three words), which is concise but lacks structure. It earns its place by being minimal, but it provides no additional context or sentence structure. A score of 3 reflects that it is adequately short but does not help the agent 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 tool has 0 parameters, no output schema, and no annotations, the description is severely incomplete. It does not explain how to use the tool, what happens upon creation, or any prerequisites. For a tool that creates a resource, this is insufficient.

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 is empty with 0 parameters, so schema coverage is 100%. The description does not add meaning beyond the schema, but with no parameters, there is nothing to describe. Baseline 4 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 une facture' clearly states the verb and resource, distinguishing it from sibling tools like create_client or create_opportunity. It is not a tautology because it adds the French language version, but it essentially restates the tool name.

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. It lacks context on prerequisites, ordering, or scenarios. The agent must infer usage from the tool name alone.

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 (readOnlyHint, destructiveHint, etc.) and the description does not disclose any behavioral traits such as side effects, required permissions, or whether the creation is reversible. For a mutation tool, this is insufficient disclosure.

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), which is acceptable, but it lacks critical details that could be included without much bloat. It does not front-load any key information beyond the basic action.

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 many sibling creation tools, the description fails to explain what an opportunity is or how it relates to other entities. No output schema is provided, but the description does not mention return values or expected 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?

Schema description coverage is 100%, so the schema already documents parameters adequately. The description adds no additional meaning beyond the schema, meeting the baseline expectation but not exceeding it.

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' restates the tool name and indicates creation of an opportunity, but does not distinguish it from sibling tools like create_quote or create_invoice. The verb and resource are present, but the scope or specifics of what an 'opportunity' entails are missing.

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 create_quote or create_invoice. The description offers no context or conditions for usage, leaving the agent uninformed about the appropriate scenario.

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, and the description does not disclose any behavioral traits such as side effects, required permissions, or return behavior. This leaves the agent with insufficient information for safe invocation.

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 sentence, which is concise. However, it is in French while the tool name is in English, which could cause confusion. It is front-loaded with the essential action.

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 complex nested input schema and no output schema, the description is insufficient. It does not explain what constitutes an order, the return value, error conditions, or any additional context needed for correct usage.

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?

While schema coverage is 100% for top-level parameters, the nested objects (items, product_id, etc.) lack descriptions. The description adds no meaning beyond the schema, and the nested parameters are effectively undocumented.

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

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

The description 'Créer un bon de commande' clearly indicates the tool creates a purchase order, matching the name. It distinguishes it from siblings like 'create_invoice' or 'create_quote', though it lacks specificity about the order 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 on when to use this tool versus alternatives. There is no mention of prerequisites, context, or when not to use it, leaving the agent to infer usage from the schema alone.

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 the tool is not read-only and not destructive. The description adds no further behavioral context (e.g., authorization needs, rate limits, side effects), so it provides minimal 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) but omits essential information for a tool with many parameters. It is under-specified rather than concise, failing to earn its 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 parameters, no output schema, minimal annotations), the description lacks completeness. It does not explain return values, error handling, or idempotency, leaving significant gaps for an agent.

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

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

The schema has 100% coverage in terms of fields present but lacks descriptions for individual parameters beyond the top-level body. The description does not clarify the meaning of fields like 'unit', 'valuation_method', or 'threshold', leaving the agent to infer from names alone.

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 produit (catalogue stock)' clearly indicates creating a product in the stock catalog, with a specific verb and resource. It distinguishes itself from sibling 'create_*' tools like create_client or create_invoice.

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 or any prerequisites. It only states the action, leaving the agent without context for decision-making.

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 provide no behavioral hints (all false), and the description adds no value beyond stating the tool's basic action. No disclosure of idempotency, mutability, or side effects.

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 at the expense of necessary detail. It is under-specified and does not effectively convey the tool's functionality.

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 (nested objects with multiple required fields), the description is completely inadequate. It fails to explain required fields, data relationships, or the outcome of calling 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 top-level parameter 'body' is described as 'Request body' in the schema, which is minimal. The description does not explain any nested fields (e.g., client_id, items) or how they relate to quote creation. Despite 100% schema coverage, the description adds no semantic meaning.

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 tautology of the tool's name. It provides no additional detail about what the tool does, and fails to distinguish it from sibling tools like convert_opportunity_to_quote or invoice_from_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 offers no guidance on when to use this tool versus alternatives. Sibling tools include accept_quote, convert_opportunity_to_quote, and invoice_from_quote, but no context is given for when creating a quote is appropriate.

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 provide no hints (all false), and the description only says 'create an IT ticket'. It does not disclose that the tool performs a write operation, any required permissions, side effects, or what the response contains. Minimal 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 a single short sentence, which is concise, but it sacrifices necessary detail. While efficient, it fails to convey critical information, making it insufficient rather than appropriately 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?

Given the complex nested input schema and no output schema, the description is severely incomplete. It does not explain return values, error conditions, or the overall process. The tool's real purpose (creating a sales transaction) is not reflected, leaving an agent with insufficient context to use it 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 description adds no meaning to the parameters. The schema has only a top-level description 'Request body' for the 'body' parameter, but nested fields (cart_lines, payments, session_id) are left entirely unexplained. The description does not clarify their purpose 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 states 'Créer un ticket IT' (create an IT ticket), but the input schema includes cart_lines, payments, and session_id, which are typical of a sales receipt or order, not an IT support ticket. This mismatch makes the purpose misleading rather than clear.

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 other create tools (e.g., create_order, create_invoice). There is no mention of prerequisites, alternatives, or scenarios where this tool is appropriate.

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. Description adds no behavioral context beyond annotations, only restates the name.

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 short (3 words) but under-specified. Conciseness should not sacrifice informative content; this is insufficient for agent understanding.

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 any description of what alerts are returned, their scope, or any contextual details. Extremely incomplete for a tool that likely has a distinct purpose among siblings.

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

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

Input schema has zero parameters with 100% coverage. No parameter documentation needed; baseline score of 4 applies as description is not required to add param 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?

Description 'Alertes du dashboard' is essentially a tautology of the tool name 'dashboard_alerts'. It adds no specific verb or resource differentiation.

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

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

No mention of when to use this tool vs alternatives. Sibling tools like list_stock_alerts and dashboard_kpis exist but no differentiation is 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, idempotentHint, and destructiveHint, covering safety and mutability. The description adds no behavioral details beyond that, but does not contradict annotations. Acceptable baseline given annotation coverage.

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 with no wasted words. It could benefit from a minor reformulation to be more active, but remains efficient and 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?

Despite simplicity, the description fails to specify what KPIs are returned (e.g., sales numbers, employee count). Without an output schema, this missing detail forces the agent to guess or call the tool to discover the response structure.

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

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

The input schema has zero parameters with 100% description coverage, so schema alone fully documents the parameterless interface. The description does not need to add parameter info; baseline 4 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 'KPIs du dashboard principal' clearly identifies the tool as retrieving KPIs of the main dashboard, distinguishing it from sibling tools like 'dashboard_alerts' and 'stock_dashboard'. However, the verb is implied rather than 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 is provided on when to use this tool versus alternatives. The description does not mention any prerequisites, exclusions, or alternative tools, leaving the agent to infer usage context.

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

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

Annotations already indicate destructiveHint=true, so the tool's potential for mutation is clear. The description adds value by explaining how parameters are passed (path and body mixed in `params`), but does not disclose additional behavioral traits such as error handling, response format, or permissions. No contradiction with annotations.

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

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

The description is concise with four sentences, each serving a clear purpose: purpose, action format, usage guidance, and parameter handling. It is front-loaded and wastes no 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?

Given the tool is a generic executor with no output schema, the description covers key aspects (purpose, usage, parameter handling) but lacks details on return values, error handling, or success/failure behavior. The instruction to use help partially compensates, but agents may need more context to use it confidently.

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

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

The input schema has 100% description coverage, so the schema already documents both parameters. The description adds minimal extra semantics: it reiterates that params include path and body, and advises using eyeot_help for details. This doesn't significantly enhance understanding 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 clearly states the tool's purpose: 'Exécute une action eyeot ERP par son nom canonique.' It specifies the verb (execute), resource (eyeot ERP action), and provides the canonical format with examples. It distinguishes from sibling tools by being a generic executor for any supported action, while siblings are specific to particular 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?

The description explicitly instructs to always use eyeot_help first to know the action and expected parameters. This provides clear context for when to use this tool. However, it does not explicitly state when not to use it or mention alternative sibling tools as direct alternatives, which slightly reduces completeness.

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. The description adds detailed behavioral context: returns module list/count, actions list, or action detail depending on input. No contradictions.

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 in French, front-loaded with the main purpose, each sentence adding meaningful information without 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 the tool's simplicity (no required params, no output schema), the description covers all usage modes and outputs comprehensively. No gaps.

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

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

Schema coverage is 100%, but the description goes beyond by providing concrete usage examples for each parameter (module='rh', action='rh.employes.create', search='facture') and explaining the corresponding output 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 clearly states it is a catalog of available actions on eyeot ERP, distinguishing it from sibling eyeot_call which executes actions. It specifies different input modes and their outputs.

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 always call eyeot_help BEFORE eyeot_call to discover the exact action, providing clear when-to-use guidance. Also describes usage with no args, module, action, or search.

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, so the agent knows it's safe. The description adds no behavioral context beyond that, such as what the returned data contains or error handling. With annotations present, the bar is lowered, but the description contributes nothing new.

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 sentence, no filler. Every word serves a purpose. Highly concise and 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?

Given the tool's low complexity (one parameter, no output schema), the description is minimal but sufficient for basic understanding. However, it could be improved by mentioning the return value format or expected client ID format. Without an output schema, some description of the response would help completeness.

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

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

Schema coverage is 100% for the single parameter (client_id). The description does not add any additional meaning or format details 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?

Description uses a specific verb 'récupérer' (retrieve) and resource 'client par id', clearly distinguishing it from siblings like list_clients or create_client. It precisely indicates what the tool does.

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

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

No guidance on when to use this tool versus alternatives. With sibling tools like list_clients and search, a brief note on when to prefer this tool (e.g., when you have a specific client ID) would be helpful. Currently, the description only states the action without 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 are minimal (all false) and description provides no additional behavioral traits such as whether the quote is modified, idempotence, or required permissions. The agent learns nothing beyond 'creates an invoice'.

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 sentence, no extraneous information. Efficient but could be more structured (e.g., bullet points for parameters).

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

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

With no output schema and minimal description, the agent lacks context on return values, side effects (e.g., quote status change), and prerequisites. Incomplete for a mutation tool.

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

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

Schema coverage is 100% (one parameter), so baseline is 3. The description does not add meaning beyond the schema's '(path parameter)' label, which is not helpful. The tool description itself does not explain the parameter.

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

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

Description states 'Create an invoice from a quote', clearly indicating the action and resource. It distinguishes from sibling 'create_invoice' by specifying the source (quote). However, the French language may hinder some 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 on when to use this tool versus alternatives like 'create_invoice' or 'accept_quote'. The description lacks context on prerequisites or typical workflows.

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

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

The description adds no behavioral info beyond annotations. Annotations already indicate read-only, non-destructive, idempotent behavior. The description's minimal 'Lister les clients (CRM)' does not contradict but provides no extra 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 extremely concise, using a single sentence with no unnecessary words. Front-loads the action and resource effectively.

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 (no params, no output schema, annotations covering safety), the description is minimally adequate. However, it lacks details about return format, pagination, or scope (e.g., all clients or subset), leaving some ambiguity for a list 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?

With zero parameters and 100% schema coverage, the baseline is 4. The description adds nothing about parameters, which is acceptable since 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 clearly states the verb 'Lister' (list) and the resource 'clients' with CRM context, making the purpose clear among sibling list tools. However, it could be more precise about listing all clients versus a filtered set.

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 get_client or other list tools. The agent must infer usage from context, which is insufficient.

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

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

The description adds no behavioral context beyond what is already provided by annotations. It does not mention the scope of the employee list (e.g., all employees, active only) or any side effects.

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 too minimal to be useful. While short, it consists only of a restatement of the tool name and does not provide informative content that earns its place.

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 of the tool (no parameters, no output schema), the description could still clarify the nature of the output or any default behavior. The current description is inadequate for a 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%. According to guidelines, the baseline for 0 parameters is 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 'Lister les employés' is a tautology that restates the tool name 'list_employees' without adding specificity. It does not differentiate the tool from sibling tools such as 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?

No usage guidance is provided. The description does not indicate when to use this tool versus alternative list tools, nor does it specify any prerequisites or filters.

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 beyond the annotations. It does not describe any side effects, authentication needs, or data limitations.

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 with no redundancy or unnecessary words. It is front-loaded with the core action and resource.

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 parameters, presence of annotations, and no output schema, the description is minimally complete. However, it does not specify whether the list is global, filtered, or paginated. With many sibling listing tools, more context (e.g., 'Lists all invoices in the system') would improve completeness.

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

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

The input schema has zero parameters, so schema description coverage is 100%. No additional parameter semantics are needed, and the description does not add any (nor does it need to). Baseline is 4 for tools with no 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 'Lister les factures' clearly means 'List invoices', specifying the verb (list) and resource (invoices). It implicitly distinguishes from sibling tools like list_clients, list_employees, etc., as each targets a different entity.

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. It does not mention any conditions, prerequisites, or scenarios where list_invoices is preferred over other 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 provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety and idempotency. The description adds no extra behavioral context, which is acceptable but does not raise the score beyond the baseline.

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 (four French words). While not verbose, it lacks any structure or additional context that could improve usability. It is adequate but minimal.

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 carries the full burden. It does not specify the scope (e.g., all leaves, pending leaves) or any output format, leaving the agent with incomplete information for a list 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, and schema description coverage is 100%. With zero parameters, the description does not need to add parameter semantics, and the baseline score of 4 applies.

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

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

The description 'Lister les demandes de congés' clearly indicates the tool lists leave requests. It distinguishes from sibling list tools like list_clients or list_employees, though it does not elaborate on scope or filtering.

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

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

There is no guidance on when to use this tool versus alternatives like request_leave or other list tools. An AI agent would need to infer usage from the tool name alone.

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, effectively communicating the safety profile. The description adds no extra behavioral context (e.g., pagination, data freshness), but it does not contradict 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 extremely terse but lacks substantive content; it repeats the name without providing value. Conciseness should not come at the cost of informativeness, and this is 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 tool has no parameters and no output schema, the description is minimally adequate. However, it could be improved by clarifying the scope (e.g., 'lists all opportunities') or return format. As is, it leaves the AI agent with basic 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?

With 0 parameters, the schema is fully covered (100%). The description need not add parameter details, so the baseline of 4 applies.

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

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

The description 'Lister les opportunités commerciales' essentially restates the tool name 'list_opportunities' without adding specificity. It does not distinguish from sibling tools like list_clients or list_products, lacking a clear scope or verb beyond the name.

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. With many sibling list tools, explicit context about usage or exclusions is missing.

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, idempotentHint=true, and destructiveHint=false, which sufficiently convey safety. The description adds no additional behavioral context (e.g., pagination, sorting), but given the strong annotation signal, this is minimally 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?

The description is a single short sentence, which is concise and front-loaded. However, it is in French, which may reduce clarity for English-speaking agents, but conciseness itself is good.

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

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

With no output schema and no description of return format, the description leaves the agent uninformed about what the tool returns. For a simple list tool, it is incomplete.

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% (trivially). The description adds nothing beyond the schema, but with zero parameters, the baseline of 4 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 'Lister les bons de commande' clearly states the tool's action (list) and resource (orders). It is specific and distinguishes from sibling tools like list_clients or list_products, though it does not elaborate on scope.

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., search). The description provides no context for appropriate usage, which is a significant gap.

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

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

Annotations already declare the tool as read-only and idempotent. The description does not add any behavioral context beyond what the annotations provide, such as return format, performance implications, or pagination behavior.

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 and front-loaded, consisting of a single phrase. It earns its place but lacks some detail for completeness. It is appropriately concise 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?

Given the tool's simplicity (0 parameters, no output schema, annotations providing safety), the description is minimally adequate. It states the resource and action but does not mention scope (e.g., all products or paginated) or return format. For a straightforward listing, this is acceptable but not thorough.

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 in the input schema (100% coverage). With 0 parameters, the baseline score is 4. The description does not need to add parameter semantics since there are none to explain.

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 states the action (list) and the resource (products/catalogue). It distinguishes this tool from siblings like create_product and other list_* tools by specifying the resource.

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, such as when to use list_products vs. search or other list tools. There is no mention of exclusions or prerequisites.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, so the description does not need to add much. It adds no behavioral context beyond the purpose, but does not contradict 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 extremely concise at one short phrase, with no unnecessary words. It is efficient and front-loaded.

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

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

The tool is simple (no parameters, no output schema), but the description doesn't clarify what is listed (all quotes? any ordering?). It is minimally functional but lacks detail on the scope or format of the output.

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 (schema coverage 100%), so the description does not need to add parameter details. Baseline score 4 applies.

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

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

The description 'Lister les devis' clearly states the action (list) and resource (quotes). It is a direct translation of the tool name, but does not provide additional detail to distinguish from sibling list tools, which is a minor gap.

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 list_invoices or list_products. The description does not mention any prerequisites or context for invocation.

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, and idempotentHint=true. The description adds no additional behavioral traits beyond restating the tool's name. It does not mention return format, pagination, or other behaviors.

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 two words. It adds minimal value but is not wasteful. For such a simple tool, this level of brevity is acceptable.

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 description of what the alerts contain or how they are structured, the description is incomplete. Even for a simple list tool, more detail about the data fields returned would enhance usability.

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

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

With 0 parameters and 100% schema coverage, baseline is 4. The description confirms the tool's focus on alerts, which matches the expected lack of 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 'Alertes stock bas / rupture' clearly indicates the tool lists low stock or out-of-stock alerts. It distinguishes from sibling tools like list_products 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 when-to-use or alternative guidance is provided. The purpose is clear, but an agent would not know when to prefer this over stock_dashboard or other 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, idempotentHint, destructiveHint, so the safety profile is clear. The description adds no additional behavioral context (e.g., return format, pagination).

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 phrase, no wasted words. However, it is in French while the tool name and sibling tools are English, which may cause inconsistency.

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 list tool with no parameters and no output schema, the description lacks details about what data is returned (e.g., fields, sorting). Annotations cover safety but not output expectations.

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% (empty). The description does not need to explain parameters, but could mention that all suppliers are returned.

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 fournisseurs' clearly conveys the action (list) and resource (suppliers), but does not distinguish from sibling tools like list_clients or list_products.

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 search or other list tools. No prerequisites or 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 already indicate read-only, idempotent, and non-destructive behavior. The description adds no additional behavioral context beyond what annotations provide, and does not mention any side effects or 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 short (4 words). It is not wasteful but it is also minimal, providing only the basic purpose without enrichment. It earns its place as a statement of purpose but lacks depth.

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 (no parameters, no output schema), the description is adequate at a basic level but fails to inform about the nature of the ticket list or expected output. More context would improve usability for an 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?

There are zero parameters, so the baseline is 4. The description does not need to add parameter information, and the schema coverage is 100% vacuously.

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' clearly states the verb (list) and resource (IT tickets). It is specific enough to identify the tool's function, though it does not differentiate from other list tools beyond the resource 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?

The description provides no guidance on when to use this tool versus alternatives. With over 25 sibling tools including create_ticket and various list tools, there is 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows it's a safe, non-destructive read operation. The description adds minimal extra context beyond stating it retrieves a PDF, which is already implied by the tool name.

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, efficient sentence with no redundancy. However, it could be slightly more structured (e.g., 'Returns the PDF file for the specified quote.') without increasing length significantly.

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 covers the basic purpose but omits details about output format (e.g., binary, URL) and preconditions (e.g., quote must exist). It is minimally complete but not rich.

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; the schema already provides all necessary information. Baseline score 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 'Récupérer le PDF d'un devis' clearly states the action (retrieve) and the resource (PDF of a quote). It distinguishes itself from sibling tools like list_quotes and create_quote by specifying the output format.

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 list_quotes or invoice_from_quote. The description does not mention prerequisites like the need for an existing quote or that the tool returns a PDF file.

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 readOnly hint, etc.) but the description adds no behavioral context such as side effects, permissions, or constraints like overlapping leave checks.

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 with no wasted words. However, it is too brief to be fully effective, earning a slight deduction.

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 (7 parameters, nested objects, no output schema), the description is vastly insufficient. It fails to explain the creation action, return behavior, or any constraints, making it nearly useless for an 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?

Although schema coverage is reported as 100%, the actual schema lacks descriptions for individual parameters beyond the body object. The description does not explain any parameter semantics, leaving agents uninformed about required fields like start_date, end_date, and type.

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' is a tautology, essentially restating the tool name in French without adding any clarifying detail or distinguishing it from siblings.

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

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

The description provides no guidance on when to use this tool versus alternatives like list_leaves. No prerequisites or context 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 and idempotentHint=true, so the safety profile is clear. However, the description adds no behavioral context beyond that, such as what the search returns, whether it supports fuzzy matching, or how it handles empty results.

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, which is concise and front-loaded. However, it could include more detail without becoming verbose, such as a simple example or clarification of modules searched.

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 input schema parameters and no output schema, the description is insufficient for an agent to understand how to invoke the search or what results to expect. The vague 'cross-module' phrase and lack of examples leave major gaps in completeness.

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

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

There are no parameters (schema coverage 100%), so the description doesn't need to explain individual params. However, it fails to clarify how the search query is specified—whether via context, natural language, or implicit—which is a critical gap for a search tool.

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 'Global cross-module search' indicates a search across modules, which is a specific verb+resource. However, it lacks detail on which modules are included and what entities are searchable, making it vague compared to sibling list tools like list_clients.

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 instead of the many sibling list tools (e.g., list_clients, list_opportunities). The agent is left to infer usage without any context about what distinguishes search from listing.

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-only behavior. The description adds minimal context beyond 'KPIs'. No contradictions, but limited added 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 concise with only three words. While efficient, it could be slightly more descriptive without losing 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 has no parameters and no output schema, the description is the sole source for understanding return values. It only mentions 'KPIs', leaving agents uncertain about what specific data is provided. More detail is needed for completeness.

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

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

There are no parameters, so the input schema fully documents them. The description does not need to add parameter semantics, and it provides no misleading 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?

The description 'Dashboard stock (KPIs)' indicates the tool provides stock KPIs on a dashboard, but lacks a clear verb and does not specify the exact scope. It differentiates from siblings like 'dashboard_kpis' and 'list_stock_alerts' by mentioning stock, but is still vague.

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 does not mention any 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 indicate the tool is not read-only, not idempotent, and not destructive (destructiveHint=false). However, the description does not clarify what effects the update has (e.g., partial update vs full replacement), nor does it mention auth requirements or error behavior. The description adds no behavioral context beyond what annotations imply.

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 in French. It is front-loaded and contains no unnecessary words. However, it could benefit from a brief English translation or additional context without becoming overly 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 complexity of the input schema (nested object with many fields) and the lack of an output schema, the description is too minimal. It does not explain return values, error conditions, or authentication requirements, leaving significant gaps in understanding for an 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?

With 100% schema description coverage for top-level parameters (body and client_id have descriptions), the baseline is 3. The description does not add any additional meaning or usage hints for the nested properties within body, but the schema itself provides property types and constraints.

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' clearly indicates the action (update) and resource (client). It is simple and unambiguous, though it does not explicitly differentiate from sibling tools 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?

The description provides no guidance on when to use this tool versus alternatives, such as when to update vs creating a new client. 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?

The description aligns with annotations (readOnlyHint, idempotentHint, destructiveHint). It adds valuable context about the data retrieved and the recommended call order, enhancing transparency 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 extremely concise: two short sentences with no unnecessary words. The imperative instruction is front-loaded and every sentence adds value. It is a model of 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 no parameters, no output schema, and strong annotations, the description is complete. It explains the tool's purpose, its output (user, org, permissions), and when to use it. No additional information is needed for an agent to use it 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?

There are no parameters, so the schema coverage is 100%. The description does not need to add parameter semantics. With 0 parameters, a baseline of 4 is appropriate as it fully accounts for the schema completeness.

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 retrieves the authenticated user, active organization, and permissions. It is specific and distinguishes the tool from any sibling by its unique purpose. The name 'whoami' is self-explanatory and the description adds precise details.

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. This provides clear guidance on when to use it and implies it is a prerequisite for other tools, effectively differentiating its usage context.

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