RNCP / RS — certifications professionnelles (France compétences)

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the agent knows this is a safe, idempotent read operation. The description adds value by disclosing the history-start constraint ('history starts at the first ingestion run'), which is behavioral context beyond the annotations. It does not describe pagination behavior (limit up to 100) or potential latency, but with strong annotation coverage, a 3 is appropriate.

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

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

The description is concise at two sentences plus an example. The first sentence states purpose and scope, the second lists filters, and the example provides a concrete usage case. No word is wasted, and the structure is front-loaded with the core 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 tool has 5 parameters (1 required), 2 enums, no output schema, and annotations that cover safety, the description is reasonably complete. It explains the result type (certifications with changes), the temporal scope, and available filters. The lack of output schema is mitigated by the description indirectly hinting at the result structure. A minor gap is not explaining that 'limit' caps results and its default, but overall sufficient 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?

Schema description coverage is only 20% (only the 'since' parameter has a brief description), so the description must compensate. The description lists filterable parameters (change type, register, NSF code) but does not explain their format, constraints (e.g., 'nsf' maxLength 4, enum values for type and repertoire), or default behavior (limit default 50). The example uses a natural language query that maps to parameters, adding some value, but the description does not fully cover the schema gaps.

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 specific verbs (created, updated, deactivated, reactivated, removed) tied to a clear resource (certifications) and a temporal scope (since a date). It distinguishes itself from sibling tools like search_certifications (list vs search) and get_certification (single vs list). The mention of history start and filters for change type, register, or NSF code adds precision.

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 states when to use the tool (querying certifications that changed since a date) and provides concrete filter options (change type, register, NSF code). However, it does not explicitly say when NOT to use it versus siblings like check_habilitation or compare_certifications, nor does it mention prerequisites or alternatives. The example query helps but lacks exclusions.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, but the description adds significant behavioral logic: it clarifies that habilitation is effective only if the certification is active AND the partner state is 'Actif', and describes role detection and certifier detection. 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 and front-loaded: a direct question, two additional clarifying sentences (certifier detection and validity condition), and a concrete example. No filler, every sentence 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?

The description covers the core query, special cases, and validity conditions, making it complete for a simple lookup tool. It doesn't describe the return format, but the question 'is... habilitated... and for which role' implies the output; with no output schema, the description adequately conveys what the agent needs to know.

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 both parameters. The description reinforces the SIREN/SIRET distinction (SIREN matches all establishments) and provides a realistic example with formatted inputs, adding helpful context beyond the bare 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 what the tool does: checks if a SIRET/SIREN is habilitated for a certification and identifies the role (former, evaluer, or both). It also distinguishes itself by detecting when the SIRET is the certifier itself, setting it apart from sibling tools like check_validity or get_certification.

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 purpose is evident from the description, and the example provides a concrete use case. However, there is no explicit guidance on when to use this tool versus alternatives, nor any exclusions or comparison to sibling tools.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, indicating safe read-only behavior. The description adds significant behavioral context: it lists exact return fields, notes that CPF eligibility is only an estimate and requires extra organism habilitations, and mentions replacement certifications. This goes beyond the annotations and helps the agent understand limitations and 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 efficient: three sentences including a concrete example. It front-loads the core question, then lists return values, and closes with a practical caveat. No superfluous words. The example is helpful for non-English users, but the description could be slightly tighter by moving the example to a separate field.

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 one parameter, rich annotations, and no output schema, the description covers the essential aspects: purpose, return fields, and a key limitation (CPF eligibility is not guaranteed). It does not describe the exact response structure (since no output schema), but listing the fields is sufficient for a simple lookup tool. The example adds usability context.

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%, with the 'numero' parameter well-documented (examples of formats, maxLength, minLength). The tool description does not add further semantic meaning to the parameter beyond what the schema already provides. Baseline 3 is appropriate given full schema coverage.

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

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

The description clearly states the tool checks if a certification is currently registered/active and provides expiry details. It lists specific return fields including status, expiry date, remaining days, and CPF eligibility. However, it does not explicitly differentiate from sibling tools like check_habilitation or get_certification, which slightly reduces clarity.

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 when to use the tool (to check registration validity of a certification) via an example question. But it gives no explicit guidance on when not to use it or when to prefer alternatives among the nine sibling tools. Usage context is present but lacks exclusionary or comparative advice.

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 safety profile is clear. The description adds behavioral detail about what comparisons are performed (Jaccard overlap, closest bloc). No contradictions found.

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 dense, front-loaded sentence followed by a short example. Every word adds value, no redundancy.

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

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

For a simple two-param comparison tool with full schema descriptions and clear annotations, the description is nearly complete. Minor gap: doesn't mention output format or that it's idempotent (though annotation covers that).

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% and both parameters have full descriptions with format examples. The tool description adds no param-specific detail beyond what the schema provides, so baseline 3 is appropriate.

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

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

The description clearly states the tool compares two certifications side-by-side and lists specific metrics compared (level, status, certifiers, overlap). It distinguishes itself from siblings like get_certification (single cert) and search_certifications (query-based search).

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 this tool is for detailed comparison between two certifications. The example suggests use case (comparing two RNCP numbers). No explicit when-not-to-use or alternatives given, but the sibling context and parameter names make it clear.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows it's a safe read. The description adds behavioral context: long texts are truncated to 4000 characters unless full=true. This is useful but not extensive; no contradictions with annotations.

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

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

Description is concise: two sentences plus an example. It front-loads the list of output fields, then states the truncation rule, then gives an illustrative example. Every sentence adds value; no redundancy.

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

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

No output schema exists, so the description must clarify return values. It does: lists all included fields (title, level, status, etc.) and notes truncation behavior. For a two-parameter tool, this is complete and sufficient for an agent to understand what to expect.

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

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

Schema coverage is 100% (both parameters described). The description adds meaning by explaining the effect of the full parameter on truncation behavior, which is not in the schema. For the numero parameter, the schema already provides thorough documentation.

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 clearly states the tool returns a 'full structured sheet' for one RNCP or RS certification, listing specific fields. It distinguishes from sibling tools like search_certifications (search) and compare_certifications (compare) by focusing on fetching a single certification's detailed sheet.

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 an example use case in French, implying usage for retrieving a specific certification. However, it does not explicitly state when to this tool versus alternatives like search_certifications or compare_certifications, nor when not to use it.

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

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

Annotations already indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds transparency by listing the exact data points returned (date, ingestion run, counts, age), which is useful beyond the annotations. There is no contradiction between description and 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 two sentences long, front-loaded with the most important information, and includes a concrete example. Every sentence adds value: the first lists what data is returned, the second tells when to use it. No wasted words.

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

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

Given the tool has no parameters and no output schema, the description fully explains what the tool does and what it returns. It is sufficient for an AI agent to understand the purpose and output. The example further clarifies the expected query format.

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

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

The tool has zero parameters, so the input schema is trivially 100% covered. The description does not need to explain parameters. The description adds value by specifying the kind of information returned, which is effectively the 'output' semantics. Baseline for 0 parameters is 4.

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

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

The description clearly states the tool returns 'source dataset date, ingestion run, counts (total/active/RNCP/RS/blocs/partners) and age of the data in days.' It also provides a concrete usage example ('De quand datent les données RNCP ?'), making the purpose unambiguous. The tool's name 'get_data_status' is accurately reflected, and it is distinct from sibling tools like 'get_certification' or 'list_blocs' which focus on specific entities.

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 says 'Call this to tell the user how fresh the answers are,' which is a clear usage guideline. It includes a realistic example question in French. While it does not provide 'when not to use' or contrast with siblings, the use case is specific enough that an AI agent can infer when to invoke it.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value by specifying the output format (order and wording for EDOF) and the special case for RS certifications. However, it does not disclose behavior for invalid inputs, non-existent certifications, or edge cases like empty results. The added context is useful but not rich enough to warrant a higher score.

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 sentences plus an example in parentheses. It front-loads the key information (what the tool returns, the ordering, and the RS exception). Every sentence earns its place; there is no fluff or repetition. The structure is efficient and easy to scan.

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 has one parameter, no output schema, and annotations cover safety. The description explains the output components and ordering, but does not specify the exact return structure (e.g., array of objects, pagination, error handling). It also leaves ambiguity about what happens when an RS certification number is provided (returns empty list? error?). While adequate for a simple list tool, the missing output schema and lack of explicit error behavior make it minimally complete.

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

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

The input schema has 100% description coverage, with the parameter 'numero' already documented with formats (RNCP, RS, etc.). The tool description adds context about the tool's purpose (RNCP vs RS) but does not add new meaning about the parameter itself beyond what the schema provides. According to the scoring guidelines, when schema coverage is high, the baseline is 3, and the description does not sufficiently elevate 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 clearly states the tool lists 'blocs de compétences' for an RNCP certification, including the components (code, title, skills, assessment methods) and the specific ordering for EDOF forms. It distinguishes from RS certifications by noting they have no blocs. However, it does not explicitly differentiate from sibling tools like 'get_certification', which might also return bloc information, so clarity is high but not full.

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 when to use: for RNCP certifications where blocs are needed in EDOF order. It explicitly excludes RS certifications ('RS certifications have no blocs'), giving a clear negative case. However, it does not mention alternatives (e.g., when to use get_certification instead) or provide guidance on when not to use this tool beyond the RS exclusion. The usage context is implied, not fully articulated.

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 safety profile is clear. The description adds that results are paginated and filtered by SIRET prefix, which is useful. However, it does not disclose pagination limits, default ordering, or whether inactive partners are included when actifs_only is false, leaving some behavioral gaps. With annotations covering the main safety aspects, a score of 3 is appropriate.

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

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

The description is two sentences plus an example, all highly relevant. Every piece serves a purpose: enumerating output fields, mentioning pagination and filtering, and giving a use case. No wasted words.

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

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

For a read-only list tool with good annotations and a clear schema (5 parameters, no nested objects, no output schema needed), the description covers the main intent, filtering, and pagination. It is slightly lacking in details about the default behavior of actifs_only and the meaning of offset, but overall sufficient for an agent to use it correctly in most queries.

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 only 40% (two of five parameters have descriptions: numero and siret_prefix). The tool description adds context about the SIRET/SIREN filter and the example, but does not explain limit, offset, or actifs_only beyond what the schema provides (defaults and types). Given the low coverage, the description does not fully compensate, but partially helps with the filter parameter. Baseline adjusted downward slightly for the gap.

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 explicitly states the tool lists training organisms habilitated on a certification, specifying the data returned (name, SIRET, role former/evaluer/both, state, dates) and provides a concrete example query. This clearly differentiates it from sibling tools like search_certifications or check_habilitation.

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 mentions pagination and filtering by SIRET/SIREN prefix, offering guidance on how to refine queries. However, it does not explicitly state when NOT to use it (e.g., for checking validity of a single partner, which would use check_validity or check_habilitation), or provide alternatives among siblings.

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 discloses that the search uses BM25 + French synonyms, which adds value beyond the readOnlyHint and idempotentHint annotations. It mentions that RS entries have no level and that results include status and expiry date. No contradictions with annotations.

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

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

The description is concise: three sentences covering purpose, filters, and what is returned. It front-loads the core action and ends with a helpful example. No superfluous 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?

Despite having 7 parameters and no output schema, the description covers the essential behavioral aspects: search algorithm, registers, filters, example query, and what the return includes (ranked matches, status, expiry). It also clarifies nuances like RS having no level. This is sufficient for an agent to use the tool correctly.

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

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

Schema coverage is high (86%), and the description provides additional context by stating filter capabilities and an example French query. It clarifies that niveau only applies to RNCP and that limit has a default of 10. This adds meaning beyond the raw 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 performs full-text search over RNCP and RS certification registers, using verbs like 'search' and 'filter'. It distinguishes from the sibling tool get_certification by noting that tool is for details. The purpose is specific and unambiguous.

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

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

The description implies usage context by stating it searches over both registers and can filter by register, level, NSF or ROME code. It explicitly mentions using get_certification for details, giving clear guidance on when to switch to a sibling. However, it does not explicitly exclude scenarios like checking validity or comparing certifications, which are handled by other siblings.

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