Projet Ariane — Orientation

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

The readOnlyHint annotation already covers the safety profile, so the description does not need to restate read-only behavior. It adds useful context about the data source ('Projet Ariane') and the returned sections, but it does not disclose error behavior or missing-slug handling. 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?

One concise, front-loaded sentence that names the action, the resource, and the key returned content in a compact parenthetical. Every word adds value and there is no repetition of schema details.

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

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

For a simple one-parameter, read-only tool with no output schema, the description adequately conveys what will be returned and from which data source. It could be slightly more complete by tying usage to a prior search step via rechercher_aides, but that is not necessary to invoke the tool correctly.

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

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

Schema description coverage is 100%: the slug parameter is already documented as a URL identifier with examples. The description adds no additional parameter meaning, so the 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?

States a specific verb ('retourne'), a specific resource ('fiche d'une aide financière'), and lists the contained fields (description, montant, profils éligibles, liens officiels). It does not explicitly name the sibling search tool, but the 'fiche complète' wording makes the record-lookup purpose distinguishable from a search tool.

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 given about when to use this tool versus rechercher_aides or fiche_metier. An agent must infer that this tool requires a known slug and likely follows a search step, but the description does not state that or mention any alternatives 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?

The readOnlyHint annotation already covers the safety profile, and the description confirms a read operation with 'Retourne'. It adds useful context about the data source ('données Projet Ariane') and the fields returned, but does not disclose behaviors such as not-found handling, response format, or any 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 front-loaded sentence that names the action, resource, and key content areas. Every part earns its place, and there is no repetition of the title or unrelated detail.

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

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

For a one-parameter, read-only tool with no output schema, the description is mostly sufficient: it states what is returned, the source, and the main content categories. However, it leaves sibling differentiation and usage context implicit, so an agent might need additional reasoning to choose between this and similarly named tools.

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

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

The schema provides 100% coverage for the single parameter 'slug', including a helpful example ('infirmier, developpeur-web'). The description adds no additional parameter semantics beyond what the schema already documents, so the 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 uses a specific verb ('Retourne') and resource ('la fiche complète d'un métier'), enumerating the content covered (description, rémunération, marché de l'emploi, formations associées). This makes clear it is a single-record fetch rather than a search, but it does not explicitly distinguish itself from sibling tools such as 'rechercher_metier' or 'fiche_aide'.

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 intended use—retrieving a complete job sheet for a known slug from Projet Ariane—is implied by the description, but there is no explicit guidance on when to use this tool versus siblings like 'rechercher_metier' or 'ou_se_former'. No alternatives or exclusion conditions 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 the description is consistent with a read-only lookup. It adds useful behavioral context: results are limited to diplomas/formations that give access to the requested métier/domaine and are based on Projet Ariane data. No destructive side effects or hidden mutation behavior are suggested.

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

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

A single concise sentence that front-loads the action and resource, and adds the data source at the end with no filler. Every word 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?

For a simple two-parameter read-only tool with 100% schema coverage, the description provides the key invocation context: it searches by either métier or domaine and returns formation/diploma options. It does not explicitly state what happens if no parameters are provided, but this is a minor gap given the simple schema and no output complexity.

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

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

Schema description coverage is 100%, so metier and domaine are already self-explanatory. The description adds the 'or' relationship between the two filters, but it does not explain formats, parameter combinations, or whether at least one parameter is expected.

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') and resource ('diplômes et formations'), with a clear scope: access to a given job or domain, sourced from Projet Ariane. It reads as a distinct offering from sibling tools like fiche_metier and rechercher_metier.

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

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

The description implies the tool is for answering how/where to train for a given job by listing diplomas and formations, but it never explicitly states when to prefer this tool over rechercher_metier or fiche_metier, nor any exclusions. Usage context must be inferred rather than spelled out.

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

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

With readOnlyHint=true, the tool is known to be safe, and the description adds meaningful behavioral detail: it performs situation-based matching and returns a list with monetary amounts and links to detailed fiches. It does not overstate side effects and remains consistent with the annotation.

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

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

The description is a single front-loaded sentence with no filler. It states the action, gives examples, describes the input mode, and specifies the return value, all in an appropriately compact form.

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

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

For a simple read-only search tool with no output schema, the description adequately covers the return shape (list, amounts, links). It could optionally mention empty results or eligibility caveats, but nothing essential is missing for correct invocation.

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

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

Schema description coverage is 100%, so both parameters are already documented. The description reinforces that 'situation' is free text and gives category examples, but it does not add new parameter semantics beyond what the schema already provides. Baseline 3 is appropriate.

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

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

The description uses a specific verb ('Trouve') with a clear resource ('aides financières'), enumerates representative subtypes, and states the input (free-text situation) and output (list with amounts and links). This clearly differentiates it from siblings like fiche_aide or rechercher_metier, which target single details or job information.

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

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

The description clearly indicates when to use the tool: when a person's situation is described in free text and matching financial aid is needed. It does not explicitly mention when not to use it or point to an alternative, but the context is specific enough to guide 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?

The readOnlyHint annotation already covers the safety profile. The description adds useful context by naming the data source (Projet Ariane) and stating that results include links to fiches. It does not go deeper into limits, ordering, or result format, but the annotation reduces the burden.

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

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

The description is a single concise sentence that front-loads the main purpose and output. Every word contributes value, with no filler or repetition of the title.

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 two-parameter read-only search tool, the description is largely complete: it explains what is searched, the data source, and the output format (list with links). It does not describe ordering or limits, but these are not essential for basic invocation.

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

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

Schema description coverage is 100%, so both parameters are already documented well. The description mostly restates the schema's meaning by mentioning interests and domains, without adding new format, example, or combination details.

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

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

The description states a specific action ('Trouve des métiers'), a clear resource ('métiers'), and the matching criteria ('centres d'intérêt ou un domaine'). It also signals that the output is a list of links to fiches, which distinguishes it from sibling tools like fiche_metier that likely provide individual job 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 clearly implies when to use the tool: when searching for careers based on interests or a domain. It does not explicitly name exclusions or alternatives, but the criteria 'centres d'intérêt ou un domaine' and the list-returning behavior provide enough context to differentiate from the sibling tools.

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