GlobalStart : création de société

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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent operation. The description adds meaningful behavioral context beyond them: required API key in X-API-Key or Authorization Bearer, an explicit error without a key, advisor review, written quote, and no payment collected by this call.

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

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

The description is three sentences and front-loads the core action and return reference. Each sentence earns its place by covering purpose, authentication, and the no-payment/advisor workflow.

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, the description helpfully explains the returned reference format and the downstream advisor/quote process. Combined with the fully documented input schema and annotations, it is nearly complete, though it could warn more explicitly about duplicate submissions for a non-idempotent creation 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%, so all ten parameters are already documented in the schema, including the nested agent object. The description only adds the general notion of an identified client and does not clarify parameter syntax, formats, or constraints beyond the schema.

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

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

The description states a specific verb and resource: opening a creation file for an identified client and returning a GS-AAAA-XXXXXX reference. This is clear enough to distinguish it from quote, tracking, and jurisdiction-related siblings, but it does not explicitly name or contrast those 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?

It gives useful context that the file will be reviewed by an advisor and followed by a written firm quote, implying this is the initial creation step. However, it does not explicitly say when to use this tool instead of globalstart_devis or globalstart_suivi_dossier, nor does it state 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 readOnly, idempotent, closed-world, non-destructive, so the safety profile is covered. The description adds value by disclosing the payload contents an agent will receive — pricing, lead time, included services, public page and order link — which is meaningful since no output schema exists.

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 sentence, front-loaded with the action and resource, then a compact field list. No filler, no repetition of the title or annotations.

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 single-parameter read tool with full annotations, the description covers purpose and the shape of the return value, compensating for the absent output schema. Only the retrieval workflow (list then detail) and error behavior remain unstated, which is a minor gap.

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

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

There is a single parameter and schema coverage is 100%, with the schema itself giving an example value ('royaume-uni'). The description adds nothing about slug format, valid values, or lookup behavior, so the baseline 3 applies.

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

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

The description gives a specific verb ('Donne le détail') and resource ('d'une juridiction'), then enumerates the concrete fields returned (forme de société, prix, délai, prestations, lien de commande). It is clearly distinct from siblings like lister_juridictions or creer_dossier, though it never names them explicitly.

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

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

Usage is only implied: the required slug parameter suggests a single-record lookup after a listing call, but the description never states when to prefer this over globalstart_lister_juridictions or globalstart_devis, nor what happens with an unknown slug. An agent can infer the flow but not confirm 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 establish that this is a read-only, non-destructive, closed-world operation, so the description rightly focuses on quote behavior. It adds meaningful context by listing the returned quote contents and stating that the DEV reference is valid for 7 days and that no personal data is required. It does not explain error handling or why the operation is non-idempotent.

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 that covers the action, inputs, output fields, validity period, and privacy note without waste. Every clause 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?

With no output schema, the description usefully explains what the quote contains and its 7-day validity. For a simple read-only quote tool with one required parameter, this is nearly complete, though it could clarify default formula behavior or error cases.

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 all four parameters are already documented in the input schema, including the optional formula, activity, and residence country. The description reinforces that juridiction and formule drive the quote and that no personal data is needed, but it does not add syntax or format details beyond the schema.

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

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

The description states a specific verb and resource ('Rend un devis ferme') and scopes it to a jurisdiction and formula, with the returned quote fields enumerated. This clearly distinguishes it from the sibling tools for dossiers, jurisdiction details, jurisdiction listing and case tracking.

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 context implies this tool is used to obtain a firm quote for a given jurisdiction and formula, but there is no explicit 'when to use' or 'when not to use' guidance, nor a named alternative. The note that no personal data is needed is useful but does not fully establish usage boundaries.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered structurally. The description adds the returned field set (forme, prix public, devise), which compensates for the absent output schema, but says nothing about pagination, result ordering, or volume.

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

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

Two tight sentences with zero waste: the resource and its returned fields come first, then the optional filters with their accepted values. Every clause carries information an agent needs.

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 three optional parameters, rich annotations, and no output schema, the description covers the resource, the returned fields, and the filter value space adequately. Only pagination/result-size behavior is unresolved, a minor gap for a read-only 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?

Schema coverage is 100%, so baseline is 3, and the description earns above baseline by supplying semantics the schema lacks: it enumerates the valid region values (europe, ameriques, afrique, asie, moyen-orient) and notes that the singular « amerique » is accepted, which the schema's bare "Filtre région, ex. « europe »" does not convey.

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

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

States a specific verb ("Liste") plus the resource ("juridictions") and what each entry contains (forme, prix public, devise), so an agent knows exactly what comes back. It does not explicitly contrast itself with globalstart_detail_juridiction, so sibling differentiation is left to inference from the list/detail naming.

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?

Marks all three filters as optional and enumerates accepted region values, which is genuine usage help. However it never says when to reach for this tool versus globalstart_detail_juridiction for a single jurisdiction, and gives no exclusion or prerequisite guidance.

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

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

Annotations already declare readOnly/idempotent/non-destructive, so the description's burden is lighter; it still adds the authentication requirement (email or API key) that the annotations do not convey. It does not describe error behavior when the reference is unknown, which is a minor gap for an otherwise safe read.

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

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

Two tight sentences with zero waste. The resource and returned fields are front-loaded, and the auth prerequisite follows immediately.

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, the description usefully enumerates the return fields, and the auth constraint is covered. The only thing an agent might still wonder about is failure behavior for an invalid/unknown reference.

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 baseline is 3, but the description adds a real clarification: the email is *required* at dossier level (or an API key must be supplied), which the schema's required list alone does not convey. It gives no format hint beyond what the schema's reference example already shows.

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

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

States a specific verb ('Renvoie l'état') and resource ('dossier') plus the exact fields returned (statut, étape courante, avancement, prochaine étape). It clearly differs from the create/quote/list siblings, though it never names them explicitly.

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 prerequisite ('L'adresse e-mail du dossier (ou une clé API) est exigée') is stated, which helps the agent prepare the call. However, there is no explicit when-to-use/when-not guidance and no reference to the alternative sibling tools.

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