immobilier

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

No annotations are provided, so the description must disclose behavior. It mentions the tool creates a draft and rejects publish attempts, but fails to describe side effects (e.g., does the draft persist?), authentication needs, or return format beyond 'texte_brut + html'.

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: three sentences covering condition, action, and critical warning. Every sentence adds value, no fluff, well front-loaded with the use case.

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 14 parameters, no required ones, no output schema, and no annotations, the description is too sparse. It does not guide parameter usage, explain return values, or outline workflow consequences (e.g., how to proceed with the draft). The tool is complex but the description treats it as simple.

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 7% (only 'dpe' described). The description adds no information about parameters, leaving 13 parameters unexplained. It does not clarify which are essential, how they relate to the output, or any constraints beyond the schema's enum.

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 specific verb 'rédiger' and resource 'brouillon d'annonce de location'. It distinguishes from siblings by emphasizing it only creates drafts and explicitly prohibits publishing, which is unique among listed sibling tools.

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

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

The description specifies when to use ('QUAND un bien vacant doit être mis en location') and explicitly warns against attempting publication ('aucune publication...', 'publier=true est refusé'). However, it does not mention alternative tools or scenarios when not to use it beyond the publish restriction.

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 no annotations, the description carries full burden. It discloses output format (HTML printable, PDF via API), formatting for window envelopes, and a safety check. It does not mention side effects like saving or updating, but for a document generation tool this is sufficient.

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 in original French) and front-loaded with the condition. Every sentence adds value: prerequisite, action, output, formatting, address guidance, safety rule.

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 12 parameters and no output schema, the description covers the tool's purpose and output format but omits explanations for several parameters (e.g., trimestre_nouveau, lieu). Completeness is adequate 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?

Schema coverage is low (17%). The description adds meaning for two key parameters: locataire_adresse (postal) and logement_adresse (property), and mentions zip code validation. However, other parameters like trimestres, lieu, bailleur_adresse are not explained.

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 notifies the tenant of an IRL revision via a letter. It uses the verb 'notifier' and identifies the resource (courrier de révision IRL). It distinguishes from sibling 'irl_revision_loyer' by stating to calculate first with that 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?

The description gives explicit when-to-use context ('QUAND la révision IRL est calculée et qu'il faut la NOTIFIER') and a prerequisite ('Calculez d'abord avec irl_revision_loyer'). It advises on address selection and includes a safety rule about zip codes. Alternatives are implied but not exhaustive.

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 no annotations provided, the description carries full burden. It mentions generating HTML-PDF via a POST endpoint and formatting details, but lacks disclosure of behavioral traits like auth requirements, rate limits, or error handling. The sales pitch adds unrelated noise.

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 front-loaded with the core purpose in the first sentence, but includes extraneous marketing content (subscription link) that could be omitted. It is not overly long but could be more 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 complexity (15 parameters, 3 required, no output schema), the description is incomplete. It lacks explanations of parameter roles, return values, or error behavior, and does not compensate for the missing annotations or output schema.

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 0% across 15 parameters, and the description provides no details about any parameters. It fails to add meaning beyond the schema, leaving the AI agent without guidance on parameter usage.

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 that the tool generates an 'AVIS D'ÉCHÉANCE' (rent due notice) as HTML/PDF, specifying the context of pre-payment. However, it does not explicitly distinguish this from sibling tools like 'quittance_loyer' or 'relance_impaye', which would help an AI agent choose correctly.

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 indicates when to use the tool ('QUAND le bailleur doit APPELER le loyer du mois avant paiement') but provides no alternatives or guidance on when not to use it. Sibling tools exist for related tasks, but no exclusions or comparisons are 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?

With no annotations, the description carries full burden. It discloses that a PDF is generated via a POST endpoint, but does not mention side effects like data modification, authorization requirements, or other behavioral traits.

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

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

The description is concise but fragmented: a single sentence, then a short phrase, then an endpoint. It front-loads the usage condition well but lacks structured formatting.

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 (12 parameters, no output schema, no annotations), the description is very incomplete. It fails to explain parameter purposes, process, or return value beyond the PDF endpoint.

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 0% (no parameter descriptions in schema), yet the description adds no meaning to any of the 12 parameters. It only mentions 'titre' is required but does not explain its role.

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's for ordering a repair to a craftsman or reporting to the owner, and identifies the tool as a 'Bon / demande d'intervention maintenance'. However, it does not explicitly differentiate from siblings like 'compte_rendu_chantier' or 'devis_travaux' beyond the name and context.

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

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

The description starts with 'QUAND' providing a clear usage condition (when a repair must be ordered or reported). But it lacks guidance on when not to use this tool or mention alternatives among the 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?

With no annotations, the description fully discloses behavior: it is a read-only GET endpoint returning public rules. It mentions no side effects, caching advice, and returns structured data with version and domaines. The REST endpoint and HTTP method are explicitly stated, providing complete 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 front-loaded with the critical usage instruction and then provides detailed return structure and context. While it is slightly long, each sentence adds value. It could be more concise, but it is well-structured and efficient.

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 single optional parameter and no output schema, the description fully completes the picture: it explains the return format ({version, domaines, urls}), content type (public rules), and endpoint (GET /api/v1/agent-playbook). It also clarifies that server-side guardrails are authoritative, adding necessary 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?

The schema already describes the only parameter 'domaine' as an optional filter with an enum of values. The description mentions a subset of domains ('securite, documents...') but does not add new meaning beyond the schema. With 100% schema coverage, this meets the baseline expectation.

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: 'FREE versioned playbook of best practices for MCP/API agents.' It specifies when to call it ('WHEN you discover this server — call it FIRST, before anything else') and distinguishes it as a public, read-only guide. This makes the purpose unambiguous and distinct from sibling tools.

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

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

Explicit usage guidance is provided: 'call it FIRST, before anything else, and again if your cached instructions may be stale.' It also clarifies that it contains no tenant data and that server-side guardrails remain authoritative, implying when not to rely on it for proprietary rules. The description leaves no doubt about when to use this tool.

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 provided, so the description must disclose behavior. It mentions output formats (HTML, PDF) and recipient, but fails to clarify the core action (e.g., creating, sending, or generating). The purpose is implied but not explicitly stated, leading to ambiguity.

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 short and contains useful keywords, but it is somewhat disorganized and mixes French and English phrasing ('Destinataire fenêtre = agence'). A more structured format (e.g., bullet points) would improve clarity.

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

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

Given 17 parameters and no output schema, the description is severely incomplete. It does not explain the tool's overall function, return values, or how to use it effectively. The minimal context leaves significant gaps for an agent to understand and 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?

With 0% schema description coverage and 17 parameters, the description does not explain any parameter meaning or usage. It completely fails to add value beyond the schema's structural definition, leaving agents without guidance on how to correctly populate fields like 'garant_nom' or 'piece_jointes'.

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 identifies the tool as a tenant application file ('Dossier de CANDIDATURE locataire') and specifies it's used when a candidate compiles their housing file. It distinguishes this from siblings by focusing on the application creation step, though explicit differentiation is 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?

The description provides a clear usage trigger ('QUAND un candidat constitue son dossier') and a post-use action ('À classer dans le dossier local après réception'). However, it lacks alternatives or when-not-to-use guidance, which is important given many 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?

No annotations provided. The description adds useful context: mentions the schema GET endpoint and that the response includes alertes[]. However, it does not disclose if the tool is read-only or has side effects, nor any authorization needs or rate limits. It adds moderate value beyond the schema.

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 paragraph that is front-loaded with the purpose. It is concise and includes essential usage guidance. Could benefit from bullet points but is not 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 tool's complexity (10 parameters, no output schema, no annotations), the description covers the purpose and prerequisite (call cao_verifier) but lacks details on the output (DXF file behavior) and response handling. The mention of alertes is helpful but 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?

Schema description coverage is high (90%), so the baseline is 3. The description does not add significant parameter information beyond the schema; it only says 'Draw a building scene' and points to the external schema endpoint. No new semantics for individual parameters.

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

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

The description clearly states the purpose: generate a real CAD file (DXF) from a building scene. It uses a specific verb ('generate'), identifies the resource (AutoCAD DXF), and distinguishes from siblings by specifying 'real CAD file' vs other outputs like PDF or renders.

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 says 'WHEN the drawing must leave as a real CAD file' and advises to call cao_verifier first. References a schema endpoint. It does not explicitly list alternatives, but the sibling context and wording imply 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?

With no annotations provided, the description carries full burden. It adds behavioral context by mentioning it returns alertes[] from a geometry audit, indicating a non-trivial side effect (audit). However, it lacks details on auth requirements, idempotency, or potential destructive actions.

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 long, front-loaded with the key trigger scenario, and contains no extraneous information. Every sentence adds value.

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

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

For a tool with 10 parameters and no output schema, the description covers the purpose and a notable output (alertes) but does not explain the return structure or how parameters affect the result, leaving some 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 description coverage is 90%, so baseline is 3. The description does not add any extra meaning to the parameters beyond what the schema already provides; it merely states the overall function.

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 computes quantities from a CAO scene and mentions specific use cases (pricing, ordering, quote checking). It also distinguishes from sibling tools by noting it uses the same scene as cao_generer_dxf but for figures, not DXF.

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 provides explicit scenarios for when to use the tool (need figures, pricing, etc.) and implicitly contrasts with cao_generer_dxf via 'Same scene as cao_generer_dxf.' However, it does not list alternatives or explicitly state when not to 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?

With no annotations, the description carries the full burden. It transparently discloses that the catalogue is free (no API key, 0 units), details the return structure ({categorie, libelle, cotes_defaut}), explains that dimensions are optional with real commercial defaults, clarifies placement semantics (z is floor level), and states where results appear (4K visit, PDF, DXF, quantities). This goes beyond basic functionality to cover important behavioral nuances.

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 long but well-structured, front-loading the primary purpose and using a categorized list to convey the catalogue contents. Every sentence adds value, though a tighter organization could reduce overall length while maintaining clarity.

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

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

For a tool with no parameters, no output schema, and no annotations, the description is remarkably complete. It covers purpose, usage context, return format, placement rules, integration with other outputs, and deduplication constraints. No critical information appears missing or ambiguous.

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 baseline for parameter semantics is 4. The description adds context about optional dimensions and the placement object ({type, x, y, z, rotation}) that will be used with the returned data, which is meaningful and compensates for the empty 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 function: it provides a free catalogue of real furniture and decoration objects for furnishing scenes. It uses a specific verb ('call this BEFORE composing mobilier[]') and resource, and explicitly distinguishes it from the alternative boites[] (bare cuboids). The scope is well-defined with item categories.

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 gives explicit when-to-use guidance: 'WHEN you are about to furnish or decorate a scene—call this BEFORE composing mobilier[]'. It also provides a clear exclusion: 'never furnish with boites[]' and advises not to duplicate plumbing fixtures already in plomberie[]. This sufficiently differentiates from alternatives.

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 provided, so the description carries full burden. It discloses that the tool generates a technical sheet with specific views, returns JSON with fields {html, alertes, alertes_ok, resume}, and embeds an orange alert banner if issues remain. It also mentions the prerequisite of calling cao_verifier. It does not explicitly state side effects (non-destructive read-like), but the context implies computation, not mutation.

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 remarkably concise: two sentences plus an IMPORTANT clause and return type. It front-loads the usage context, lists key outputs, and includes critical prerequisite info without any fluff.

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 (12 parameters, no output schema, no annotations), the description covers purpose, usage, prerequisite, and return format. It references cao_generer_dxf for scene consistency, which adds context. However, it could be more complete by describing error conditions or required parameter structure, but schema already details parameters.

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 92% (high), so the schema already explains most parameters. The tool description adds little beyond mentioning uses like 'top view' and 'optional MEP plan', which hint at parameter relevance but do not elaborate. Baseline 3 is appropriate as the description adds marginal value over 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 generates a professional technical sheet from a CAO scene, listing specific views (top view, elevations, shaded axonometric, optional MEP plan). It distinguishes from siblings like cao_generer_dxf by stating 'Same scene as cao_generer_dxf', indicating different 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?

The description explicitly says 'WHEN the design must be handed over to a client...' and emphasizes calling cao_verifier FIRST, giving clear context and prerequisites. However, it does not provide explicit alternatives or when not to use this tool beyond the sibling reference.

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 exist, so the description carries the full burden. It states the tool generates a visual preview, implying read-only behavior, but does not explicitly confirm it is non-destructive or list other behavioral traits. The description is adequate but lacking in detail.

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, front-loaded with purpose, and contains 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 11 parameters and high schema coverage, the description adequately explains the tool's output (SVG/PNG preview). It does not describe error behavior or edge cases, but for a preview tool this is sufficient.

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 82% (high), so baseline is 3. The description adds minimal parameter context beyond mentioning output format (SVG/PNG). The schema already describes parameters well, so no additional value 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 clearly states the tool's purpose: 'WHEN you want to SEE the plan before delivering it — a quick visual check that the scene is what you meant. Top-down preview (SVG/PNG) of a CAO scene.' It distinguishes from sibling tools like cao_verifier and cao_pdf.

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?

Explicit guidance is provided: 'Prefer cao_verifier before this for structured alerts; use the preview to visually double-check.' This tells when to use this tool versus alternatives.

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 no annotations provided, the description carries the full burden and does so thoroughly. It details numerous specific checks (e.g., 'openings.z used as absolute altitude instead of relative sill', 'escalier_depart_hors_batiment'), explains return format ('{ok, erreurs_schema, alertes[...], conseils, resume}'), states severity rules ('Fix severite=critique before delivery'), discloses that some checks are WARNING-level and why ('an open stairwell is a legitimate choice'), and describes the correctifs[] array with real replacement positions. It also mentions that applying fixes is possible via another endpoint, avoiding misleading the agent about this tool's own 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 a dense, unstructured paragraph that is very long. While it is front-loaded with the key usage guidance, it becomes verbose and repetitive: it mentions 'correctifs[]' multiple times, states 'free, no key' twice, and lists REST endpoints repeatedly (POST /api/v1/cao/integrite appears twice, plus the standalone documents endpoint and the REST equivalent). It lacks clear section breaks or bullet points, making it harder to scan, though all content is relevant. It is not concise, but the information is valuable.

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

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

For a tool with 10 parameters, no output schema, and no annotations, the description is exceptionally complete. It covers the purpose, the full range of checks (geometric, structural, document completeness), the return structure, the severity levels, the correction mechanism, how to apply fixes via separate endpoints, and even mentions the 'regles_archi' output. It also clarifies that certain checks are non-blocking warnings. There is no missing critical information for an agent to invoke and interpret 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 90%, so the schema already documents parameter meanings (e.g., 'murs: Walls: plan segments extruded vertically', 'ouvertures.z: Sill height (mm)'). The description does add context by explaining how certain parameters are interpreted in checks (e.g., 'openings.z used as absolute altitude instead of relative sill'), but this is more about behavioral insight than new parameter semantics. The tool description does not systematically elaborate on each parameter beyond what the schema offers, 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 provides a specific verb ('geometric audit', 'checks') and resource ('CAO scene'), and clearly distinguishes from sibling tools by naming 'cao_pdf', 'cao_generer_dxf', 'cao_rendu', 'cao_visite_plan', 'cao_visite_studio' as the tools to run after this check. It is explicit about being the pre-delivery verification step, leaving no doubt about the tool's function.

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 opens with a precise usage window: 'WHEN a scene is composed and BEFORE cao_pdf / cao_generer_dxf / cao_rendu / cao_visite_plan / cao_visite_studio', and explains it is 'the cheap check that stops a wrong plan or broken 4K visit from being delivered'. It also mentions standalone REST endpoints for specific sub-checks (POST /api/v1/cao/integrite, /api/v1/cao/documents) and the REST equivalent, giving clear when-to-use context. No exclusion criteria stated, but the positioning is 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?

No annotations are provided, so the description carries the full burden. It discloses wall-collision behavior (refused steps are explained, not silently applied), the return structure including per-action states, the API key requirement, and the free catalog endpoint. This goes well beyond basic safety hints and sets clear expectations for the agent.

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 long but tightly packed with actionable information: the WHEN clause leads, then the action grammar, starting point, scene requirement, return shape, and auxiliary endpoints. Every sentence earns its place, and the use of caps for key instructions ('PILOT', 'POST THE SCENE TOO') aids scannability without becoming noise.

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 (13 parameters, no output schema, no annotations), the description is remarkably complete. It explains the return object ({camera, etapes[], chemin[]}), the data flow from cao_visite_plan into `depuis` and from `chemin` into cao_visite_studio, the wall-collision feature, the free command catalog, and the API-key requirement. Nothing essential is left mysterious.

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 92%, so baseline is 3. The description adds meaningful context for key parameters: it explains the `actions` format ('avancer x3', 'ctrl+8', {code, repetitions}), the `depuis` source (a waypoint from cao_visite_plan), and why scene parameters matter (enable wall collision and room landmarks). It does not enumerate every scene field, but the schema already does that.

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 pilots the camera via a sequence of actions rather than coordinates, and it opens with a specific scenario (automatic visit good but ONE view wrong). It distinguishes itself from siblings by referencing cao_visite_plan for the starting waypoint and cao_visite_studio for rendering the returned chemin.

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?

Explicit when-to-use guidance: 'WHEN the automatic visit is good but ONE view is wrong... and rewriting a whole `chemin` by hand would be absurd.' It also explains how to start (from a waypoint of cao_visite_plan) and when to omit `depuis` for an overall view, plus how to feed the result to cao_visite_studio. The description navigates alternatives without ambiguity.

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

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

No annotations are provided, so the description carries the full transparency burden. It discloses critical behaviors: the endpoint refuses 400 on construction_critique, the auto path detection (walls → flood fill → room centres), that an edited chemin is used verbatim and checked, the enrichment behavior for long durations, and that rendering is done by one browser-GPU engine. It doesn't explicitly describe the return format beyond naming the fields, but the output schema is absent so it does enumerate plan structure. Strong coverage given no 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 dense and front-loaded with the key purpose and critical prerequisite, which is good. However, it is a sizeable paragraph mixing prerequisites, output-format documentation, consumption instructions, adjustment advice, and endpoint references — an agent must parse through a wall of text to extract the usage contract. The structure is linear prose rather than clearly sectioned, though it's organized enough to weigh somewhat more favorably than a bullet-dump.

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 lacking an output schema, the description documents the return shape ({plan:{objectif, cadence, plans[], chemin[]}, alertes[], resume}) and the chemin coordinates convention (position/vise in mm, CAO axes). For a complex tool with 17 parameters and rich geometry (objectif, cadence, chemin, toitures, reseaux), the description covers the operational prerequisites, failure modes, fix workflow, and consumption path thoroughly. It's complete for accurate 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 coverage is 82% and quite rich, so baseline is high. The description adds real value beyond the schema on several key params: it names the lens catalogue endpoint (GET /api/v1/cao/visite/objectifs), explains the marche interior walk threshold (~1600 mm/s unwatchable), and details duree_s behavior (path ENRICHED with exterior revolutions rather than slowed down). The chemin field is well-explained (verbatim + checked). Slight deduction because some scalar params like resolution, fps, mode are left to the schema alone, but overall the description meaningfully supplements schema 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 opens with a vivid, specific framing of the tool's purpose: directing the 4K cinematic visit of a CAO scene, choosing lens and camera path. It clearly distinguishes from siblings like cao_visite_camera and cao_rendu by specifying this is a motion-planning cinematic endpoint. The verb+resource (DIRECT a 4K cinematic visit) is precise and distinct from the sibling tools.

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

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

Excellent usage guidance. It explicitly states a mandatory prerequisite (call cao_verifier FIRST and fix every severite=critique), explains the 400 construction_critique failure reason, prescribes the exact fix endpoint (POST /api/v1/cao/integrite with params), and tells how to retry. It also gives adjustment instructions (resend with modified objectif/cadence or an edited chemin), plus the output consumption path (paste into CAO editor or window.CAD_startCinematicTour). This is unusually thorough.

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 provided, so the description must carry the full burden. It mentions the HTTP POST method and endpoint, but does not disclose side effects, authentication needs, or whether the operation is safe. This is 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 concise, at four lines, and front-loaded with the usage condition. However, it lacks clear separation between purpose, endpoint, and parameter details. Still, it is not 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 (10 parameters, no output schema, no annotations), the description is incomplete. It explains only one parameter and does not mention return values, examples, or handling of optional fields.

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 0%, so the description must compensate. It only clarifies the 'points' array structure ({libelle, statut, notes}). The remaining 9 parameters (e.g., titre, client_nom) are left unexplained. This is insufficient for a tool with 10 parameters.

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

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

The description clearly states the tool's purpose: generating a progress report for a construction site to the client. It specifies the API endpoint and the structure of the 'points' array, making it distinct from sibling tools like 'bon_intervention' or 'devis_travaux'.

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 begins with 'QUAND il faut rendre compte' (when you need to report), providing clear context for usage. However, it does not explicitly exclude alternatives or mention when not to use this tool.

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 provided, so the description must disclose behavior. It mentions the HTTP method (POST) implying creation, but does not describe side effects, permissions, or what happens to existing data. This is insufficient for a mutation tool.

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

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

The description is brief and front-loads the condition, but the inclusion of the full URL adds unnecessary length. It is adequately concise but could be more efficient.

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 high parameter count (11) and no schema descriptions or output schema, the description lacks completeness. It does not explain what the tool returns, how parameters affect output, or any prerequisites.

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 11 parameters with no descriptions (0% coverage). The tool description does not add any meaning to the parameters, only identifying 'date_rdv' as required. This is completely inadequate.

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 is for generating a 'Confirmation de rendez-vous' document when a meeting is taken and needs written confirmation. It provides the verb ('confirmation') and resource ('rendez-vous'), though it does not explicitly differentiate from sibling document generation tools.

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

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

The description includes a usage condition ('QUAND un rendez-vous est pris et doit être confirmé par écrit'), indicating when to use. However, it does not specify when not to use or mention any alternatives.

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 provided, so the description bears the full burden. It mentions the HTTP method (POST) and the pieces array structure, but does not clarify read vs. write semantics, permissions needed, or side effects. The description implies a verification check, but POST suggests a create action, causing slight ambiguity.

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 moderately concise but mixes natural language with technical API details (endpoint, pieces structure). It front-loads with 'QUAND' (when), but the layout is somewhat unstructured and redundant (e.g., repeating the document list).

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 6 parameters with 0% schema coverage, no annotations, and no output schema, the description is insufficient. It covers purpose and pieces structure but neglects other parameters and return value, making it incomplete for an agent to invoke 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 0%, so the description must compensate. It only explains the 'pieces' parameter structure (type, statut, numero, date_expiration). The remaining 5 parameters (notes, siret, agence_nom, date_emission, entreprise_nom) are not described, leaving significant 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?

Description clearly states the tool verifies artisan compliance with required documents (RC Pro, décennale, URSSAF, KBIS) before assigning a project. It specifies the verb 'vérifier' and resource 'conformité artisan', distinguishing it from sibling tools like 'bonnes_pratiques'.

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 states when to use the tool: 'QUAND il faut vérifier qu'un artisan est en règle avant de lui confier un chantier'. It provides clear context but does not mention when not to use it or suggest alternatives.

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 provided, so the description must fully disclose behavior. It mentions the report is generated (HTML/PDF) but does not clarify if this tool modifies data, requires authentication, or is read-only. The description also references data provided by the agent but does not explain 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 a single paragraph but front-loaded with the key usage condition. It is concise, covering purpose, output format, recipient, and data source without unnecessary words. However, it could be more structured with bullet points for clarity.

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

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

Given the tool has 15 parameters, no output schema, and no annotations, the description is insufficient. It does not explain the return value, how to trigger PDF generation, or the meaning of many optional parameters. The directive to direct clients to /api-ia adds confusion.

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 0%, so the description must compensate. It mentions 'recettes/dépenses/honoraires/solde' which map to four parameters, but most of the 15 parameters (e.g., lieu, agence_nom, date_emission) are not explained. The required parameters proprietaire_nom and periode are implied but not elaborated.

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 is for generating a simplified management report for the owner, with specific triggers: end of quarter, fiscal year, or upon request. This distinguishes it from sibling tools like quittance_loyer or regularisation_charges.

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 starts with 'QUAND il faut rendre compte au propriétaire' providing explicit usage context. It mentions the report is HTML with optional PDF via another endpoint. However, it does not explicitly state when not to use or list alternatives, and the final sentence about directing the client to /api-ia is somewhat ambiguous.

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 provided, so the description carries the full burden. It thoroughly describes the tool's behavior: it is an authenticated decision engine that takes prospect info and returns decisions (cible, campagne, actions). It also specifies authentication requirements (API key, X-Make-Secret or X-API-Key), cost (0 units), and constraints (never invent offers/prices).

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 dense and informative, with front-loaded purpose. Each sentence adds value, but the paragraph format could be more structured (e.g., bullet points). Still, it is efficient and avoids fluff.

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

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

Given the lack of output schema and only 17% schema coverage, the description covers when to use, authentication, behavior, and follow-up actions. It mentions that the tool decides cible, campagne, and actions[], implicitly describing the output. However, it does not explicitly state the response format or structure, which would be useful.

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 6 parameters with only 17% description coverage (only 'cible' has a description). The description adds meaning by stating 'Pass prospect info only' and implying that prospect_nom, prospect_email, prospect_entreprise are prospect info. However, it does not detail the syntax or format for each parameter, leaving some ambiguity.

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 that the tool decides what to do with prospects in an outreach scenario, using the verb 'decides' and specifying the resource 'campagne'. It distinguishes itself from siblings by being a decision engine called after collection and before email sending.

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 explains when to use this tool: after collecting prospects and before sending commercial email. It provides a sequence ('Make/n8n collects, Synergieloc decides') and a follow-up action ('envoyer_offre'). However, it does not explicitly mention when not to use it or 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?

Discloses limitations: 'Pas d'accès banque' and specifies behavior for source enum. Mentions side effects like 'proposition d'écriture comptable + prochaine action' and commercial reminder. However, without annotations, more detail on mutation/reversibility would be beneficial.

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 relatively concise and front-loaded with key usage. However, it is a single paragraph mixing usage, behavior, and technical details (REST). Could be slightly more structured with clear sections.

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?

Covers purpose and usage well but lacks detail on parameter meanings. No output schema, so description should specify return value more explicitly. Overall adequate but incomplete on parameter documentation.

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?

Description mentions only 'date + montant' and source enum, but does not explain other parameters like loyer, charges, periode, locataire_nom. Schema coverage is 0%, so description fails to compensate for missing schema descriptions.

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 records a payment declaration ('tracer l'encaissement') and specifically distinguishes from sibling tool `quittance_loyer` by saying it must be called before it. The verb 'declaration' and context 'loyer payé' make purpose unmistakable.

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 says when to use: 'QUAND le client vous dit qu'un loyer a été payé' and sequencing: 'à appeler AVANT quittance_loyer'. Also provides conditional outcomes (quittance if complete, receipt otherwise) and guidance on source parameter (extrait_bancaire).

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 no annotations, the description carries full burden. It mentions the API endpoint for PDF generation and the 'lignes' structure, but does not disclose whether the operation is destructive, idempotent, or what errors may occur.

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 short but mixes French and English, includes an endpoint reference and parameter examples, yet lacks clear formatting or prioritization of key 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 11 parameters, no schema descriptions, no annotations, and no output schema, the description covers only the tool’s purpose and one parameter’s structure, leaving significant gaps in input, output, and 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?

Despite 0% schema coverage, the description documents the structure of the 'lignes' parameter with fields {libelle, quantite, prix_unitaire, tva}. Other parameters like 'lieu', 'notes', 'objet' are left unexplained, providing partial but useful clarification.

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 is for creating a work estimate ('devis travaux') when a craftsman estimates work before client agreement. It distinguishes from invoices by mentioning 'Puis facture_facturx', though not explicitly differentiating from all sibling tools.

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

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

Provides a usage context ('QUAND un artisan chiffre des travaux avant accord du client') and hints at a follow-up tool ('facture_facturx'), but lacks explicit guidance on when not to use or alternatives among the 36 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?

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It hints at document creation ('État des lieux') and references a PDF endpoint, but it does not specify side effects (e.g., record creation), permissions, or whether the tool is read-only or destructive. Minimal behavioral context is given.

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

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

The description is concise, fitting key information (when to use, legal reference, endpoint, key parameters) into two sentences. It is front-loaded with the crucial 'QUAND' clause. However, the list-like ending could be more structured.

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 (14 parameters, no output schema, no annotations), the description is insufficient. It lacks details on return values, parameter relationships, and required inputs beyond the two mandatory fields. The PDF endpoint reference is not fully integrated.

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 schema description coverage at 0%, the description should compensate but only lists three parameters (pieces[], compteurs[], cles[]) without explaining their meaning or format. The 14-parameter schema remains largely undocumented, and the description adds little beyond the parameter names.

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: to assess housing condition at entry or exit, referencing its legal basis (decree 2016-382). It distinguishes from sibling document tools by specifying 'état des lieux' and its role in deposit retention. However, the mention of 'PDF via POST /api/v1/documents/edl' is somewhat ambiguous regarding the tool's output.

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 explains when to use the tool (entry/exit inventory) and its importance for deposit retention, but it does not explicitly exclude scenarios or mention alternative sibling tools. Usage is implied rather than clearly demarcated.

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 provided, so the description carries the full burden. It discloses that the tool is free, has no quota, is always open, and consumes no units. These are important behavioral traits for an AI agent to know. It does not detail consequences (e.g., storage of feedback) but that is reasonable for a feedback tool.

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

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

The description is concise with no wasted words. It front-loads the usage condition, then provides key details (free, quota-free, always open). Every sentence serves a purpose.

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

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

Given the simplicity of the tool (2 parameters, no output schema), the description covers purpose, usage conditions, availability, and parameter roles comprehensively. No obvious 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% with descriptions for both parameters. The main description adds context that 'message' is for the feedback in plain text and 'context' is optional indicating the concerned tool/endpoint. This adds some meaning beyond the schema but does not significantly enhance understanding beyond what the schema already provides.

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

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

The description explicitly states the tool sends feedback (retour/suggestion) for the Synergieloc application, covering remarks on tools, calculations, feature ideas, and bugs. It clearly distinguishes from sibling tools which are specific operational actions (e.g., annonce_location, avenant_revision_irl).

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 starts with 'QUAND un résultat vous semble faux, incomplet, ou qu'un endpoint plante', providing clear conditions for use. It also notes the tool is free, no quota, always open, and works even outside free windows. However, it does not explicitly mention when not to use or suggest alternatives.

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 provided, so description carries full burden for behavioral disclosure. Does not mention side effects (e.g., deletion, modification), required permissions, rate limits, or idempotency. Describes creation of a document but not whether it is saved externally or returned inline. Lacks transparency expected for a mutation tool with zero 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?

Description is concise (single sentence with abbreviations) but front-loads condition and type. Contains run-on structure with mixed information (condition, format, endpoint, params). Could be split into paragraphs for clarity, but remains information-dense 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?

For a tool with 8 parameters (5 required, nested objects, no output schema), the description leaves gaps: no return value explanation, no example usage, no error conditions. Sibling list is long but no explicit contrast. Adequate for domain experts but insufficient for AI agent to infer all invocation details.

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 0%. Description partially compensates by listing fields for lines[] (description, quantity, unit_price HT, vat_rate) and explaining format enum (facturx vs preview). However, misses explanation for 3 required parameters (invoice_number, invoice_date) and optional ones (notes, due_date). Does not define nested objects (buyer, seller).

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 starts with 'QUAND' specifying the exact use case (French electronic invoicing reform, EN 16931). It names the output format (PDF/A-3+XML) and distinguishes from sibling tools (e.g., devis_travaux, quittance_loyer) by standard compliance. The tool name and content align precisely.

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 states when to use: 'QUAND une facture doit être conforme à la facturation électronique française'. Provides conditional guidance via format=preview for alternative output. Does not explicitly state when not to use, but the condition implies exclusion of non-compliant invoices. Sibling context reinforces differentiation.

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 provided, so the description carries the full burden. It discloses local folder storage and the ability to generate HTML or PDF via a separate endpoint, but lacks details on authentication, side effects, or whether it saves to disk. Adequate but not comprehensive.

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—one sentence plus context notes—and front-loaded with the use case. It avoids verbosity, though it could be better organized (e.g., listing parameters or prerequisites).

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 15 parameters with no schema descriptions, no annotations, and no output schema, the description is insufficient. It provides a high-level purpose but lacks details on parameter usage, return value, or prerequisites, making it incomplete for effective tool 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 0%, yet the description adds no meaning to any parameter. It only mentions 'titre' as required without explaining its purpose or format. This completely fails to compensate for the missing schema descriptions.

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 creates a mission/worksheet (fiche mission/chantier) when a craftsman prepares an intervention or worksite. It specifies output formats (HTML, PDF via another endpoint) and local storage, distinguishing it from sibling document tools.

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

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

The description explicitly says 'QUAND un artisan prépare une intervention ou un chantier,' providing clear guidance on when to use it. It does not mention when not to use it or alternatives, but the sibling list makes the context 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It clearly states the tool is stateless, indicative, and outputs via POST /api/v1/fiscal/synthese in JSON or PDF. It also notes limitations ('dans la limite des documents/données fournis'). While it doesn't explicitly say it doesn't modify data, the stateless mention implies it's read-only. A slightly higher score is not given because it doesn't detail error handling or data retention.

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 somewhat verbose and mixes French and English, which could confuse an English-only agent. However, it is front-loaded with the key question and purpose. Some sentences could be removed or condensed without losing meaning (e.g., repeating 'indicatif' multiple times). Overall, it is adequate but not optimally 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 tool's complexity (7 parameters, no output schema, no annotations), the description provides the essential purpose and usage context but lacks detail on parameter formats and return structure. It mentions output format options (json, html, pdf) but not the structure of the JSON response. For a stateless calculation tool, this is minimally complete but leaves the agent guessing about how to interpret results.

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?

Parameter semantic coverage in the JSON schema is minimal (only 14% of parameters have descriptions). The description mentions two required parameters ('recettes_brutes + charges_deductibles') but provides no further explanation of their meaning, units, or constraints. Other parameters like 'annee', 'proprietaire_nom', etc. are not described in the schema or the description. Given the low schema coverage, the description should compensate by elaborating on parameter semantics, but it fails to do so.

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: it generates a fiscal synthesis comparing micro-foncier (30% allowance, 15,000€ threshold) and réel regime (2044 form) for rental income. The opening question explicitly addresses when a landlord would use it, and the description distinguishes it from sibling tools which are unrelated (e.g., rent receipts, maintenance reports).

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 specifies when to use the tool: 'QUAND un bailleur se demande s'il a intérêt au micro-foncier ou au réel — typiquement à l'approche de la déclaration.' It also provides clear usage boundaries: 'À titre indicatif dans la limite des documents/données fournis — ni conseil fiscal ni déclaration ; renvoyer vers un professionnel.' This tells the agent exactly when to use it and when not to rely on it as definitive 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?

No annotations are provided, so the description carries the full burden. It discloses that the tool is free and requires no units or keys, implying it is a safe read operation. However, it does not explicitly confirm non-destructiveness or detail response format beyond 'Markdown complet'. Adequate but not exhaustive.

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 concise sentences, front-loaded with the usage condition and action. Every sentence adds value 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?

For a simple read tool with one parameter and no output schema, the description sufficiently explains purpose, prerequisites, and output type. It could mention the nature of the Markdown content (e.g., length or structure), but remains adequate.

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

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

Schema coverage is 100% with a single parameter and example values. The description adds value by explaining that the slug comes from guides_liste, providing context 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 reads a full Synergieloc guide in Markdown given a slug, and distinguishes it from the sibling guides_liste by specifying it is used after that tool returns a slug.

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 states when to use: 'WHEN guides_liste has returned a relevant slug and you need the full content.' This provides clear context and differentiates from the sibling tool.

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 provided, so description carries the burden. It mentions the tool is free and requires no units/keys, which is transparent. Since it's a read-only list operation, no behavioral issues. Does not go into response details but adequate for a simple tool.

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

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

Concise two-sentence structure. First sentence gives the use case, second explains what the guides cover. Every sentence adds value, no waste.

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

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

Given no parameters and no output schema, the description fully covers the tool's context: when to use, what it lists (screen-by-screen and legal rules), and that it's free. Complete 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?

No parameters exist (0 params). Baseline 4 per guidelines. Description adds no parameter info but schema is empty, so no 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 clearly states the tool lists official guides ('Liste les guides officiels') for Synergieloc, covering screen-by-screen manuals and French legal rules. It distinguishes from sibling 'guide_lire' which is for reading a specific guide.

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 starts with 'QUAND vous ignorez comment une opération se fait' to indicate when to use (when unsure about operation or business rule). It provides clear context but does not explicitly mention when not to use or name alternatives.

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 no annotations, the description bears full burden. It discloses inputs and outputs (new rent, formula, warnings) but does not explicitly state that it is a pure calculation with no side effects or authorization needs. Adequate but could be more explicit.

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 efficiently structured in three sentences: condition, core action, and what it returns. No extraneous 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?

The description fully covers the tool's functionality: it explains the condition, required inputs, and outputs (new rent, formula, legal warnings). No missing information for a calculation tool of this 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 coverage is 100%, so baseline is 3. The description adds context: 'Fournir le loyer actuel et les deux indices IRL (INSEE)' clarifies the role of each parameter beyond the schema descriptions. It also mentions the optional charges 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?

The description explicitly states the tool's purpose: 'Révision annuelle d'un loyer d'habitation indexée sur l'IRL'. It specifies the triggering condition, inputs, and outputs, clearly distinguishing it from siblings like 'avenant_revision_irl'.

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 sets clear usage context: 'QUAND un bail arrive à sa date anniversaire et que le loyer peut être révisé.' It does not explicitly exclude other scenarios or mention alternative tools, but the context is well-defined.

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 provided, so the description carries full burden. It only states the HTTP method (POST) implying creation, but lacks disclosure of side effects, permissions required, or any behavioral traits. This is insufficient for an agent to understand the tool's impact.

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 relatively short but mixes languages and formatting (e.g., all caps 'QUAND', inline code). It could be more structured with clear sentences for each element. It earns its place but is slightly messy.

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 6 parameters, no output schema, and no annotations, the description should provide more guidance. It covers the usage condition and one key parameter group, but leaves most parameters unexplained. The tool is moderately complex and the description 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?

Schema coverage is 0%, requiring description to compensate. The description explains the 'trajets' array structure and notes 'taux_km' as optional, but other parameters (periode, vehicule, date_emission, entreprise_nom) are not described at all. Partial coverage leaves significant ambiguity.

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 indicates the tool is for logging mileage journeys and calculating indemnities, mentioning the use case of justifying trips. It specifies the endpoint and the structure of trips, which effectively communicates the tool's purpose. However, it could be more explicit with a verb like 'Create a mileage journal' instead of relying on the HTTP method.

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 a condition for use ('when trips need justification'), but does not mention alternatives or when not to use it. Sibling tools are all different in domain, so there is little confusion, but explicit guidance on selecting this tool 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?

No annotations are provided, so the description must carry the full burden. It mentions 'POST' indicating creation, but does not disclose whether the tool is destructive, read-only, or requires specific permissions. The phrase 'préparer les achats' is ambiguous about side effects. Insufficient 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 concise (4 sentences) and front-loads the usage context. It provides the endpoint and an example array structure. However, it could be more structured by explaining parameter roles. Still, it is efficient and free of fluff.

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 7 parameters, no output schema, and no annotations, the description is incomplete. It fails to explain return values, how to use most parameters, and the overall workflow. The tool's complexity demands more detail than provided.

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 0% with 7 parameters. The description only adds meaning for the 'articles' parameter by showing its structure ('libelle, quantite, unite, prix'). The other six parameters (notes, titre, date_emission, etc.) receive no explanation. The description partially compensates for low coverage but leaves significant 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 clearly states the tool is for preparing purchases for a construction site ('préparer les achats d'un chantier'), which specifies a verb and resource. It distinguishes from siblings by emphasizing the materials list and cart context, though no explicit sibling differentiation is provided.

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 gives a clear 'when to use' context ('QUAND il faut préparer les achats d'un chantier'), but lacks explicit guidance on when not to use it or alternatives. With 37 sibling tools, more differentiation would be beneficial.

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 provided, so the description carries full burden. It discloses key behavioral traits: the tool generates a document but does not store it in the database ('Synergieloc MCP n'enregistre pas le mandat en base'), and the agent must handle signing and storage. It also hints at print layout (window envelope) and a follow-up action (démarchage). This is valuable transparency for a mutation tool.

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

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

The description is relatively concise, covering the key points in a few sentences. It is front-loaded with the usage condition ('QUAND...'). However, it could be slightly more structured, as some sentences are fragmented (e.g., 'Enveloppe à fenêtre → propriétaire. Démarchage : proposez /api-ia plan Agent.'), but overall it efficiently communicates essential 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 has 16 parameters and no output schema, the description is adequate but not fully complete. It explains the workflow (generate, sign, store, envelope) and mentions a specific endpoint, but does not describe the return value or output format (e.g., document URL). For a document generation tool, this is a notable 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?

The input schema has 16 parameters with 0% description coverage (no descriptions in schema). The description does not explain any parameter meanings or provide examples. While parameter names are somewhat self-explanatory (e.g., proprietaire_nom, agence_nom), the description fails to add any additional meaning or guidance, leaving the agent to rely solely on names.

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 generates a management mandate (MANDAT DE GESTION) under the Hoguet law, specifying the output as HTML/PDF via a specific endpoint. This clearly distinguishes it from sibling tools like quittance_loyer or bon_intervention, which serve different document purposes.

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 starts with 'QUAND un propriétaire confie la gestion de son bien à une agence : c'est le contrat de départ, avant tout le reste.' This provides clear context for when to use the tool, indicating it is the initial contract. While no alternatives are explicitly named, the context implies it is the first step, effectively guiding usage.

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

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

No annotations are provided, so the description carries full burden. It states it produces a PDF via a POST endpoint but does not disclose side effects (e.g., whether it modifies data), authentication requirements, or whether it is read-only. The mention of 'solde de tout compte' implies financial calculations but behavioral impact remains unclear.

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, front-loads the purpose, and includes the API endpoint. It uses three sentences without wasted words. However, it could be more structured by explicitly listing key parameters or linking to parameter explanations. Still, it is appropriately sized.

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 (13 params, no output schema, no annotations), the description is incomplete. It does not explain required vs optional fields, the format of arrays like 'checklist' or 'solde_lignes', or the expected response. An agent cannot reliably invoke this tool without additional 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?

With 0% schema description coverage and 13 parameters, the description adds minimal value beyond mentioning the 'type' parameter (entree|sortie). Other parameters like 'lieu', 'retenues', 'checklist', etc., are not explained, forcing reliance on schema structure alone. This is insufficient for an agent to correctly populate parameters.

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

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

The description clearly states the tool generates a document for tenant move-in or move-out, including checklist and balance statement. It specifies the operation via 'QUAND un locataire ENTRE ou SORT du logement' and references the API endpoint, making the purpose unambiguous and distinct from sibling tools.

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

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

The description indicates when to use the tool (for entry or exit of a tenant). However, it does not explicitly provide when-not-to-use scenarios or alternatives among sibling tools like 'edl_etat_des_lieux', which could overlap. The guidance is clear 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?

No annotations are provided, so the description must carry the full burden. It mentions 'POST' indicating a create operation, but it does not disclose side effects, permissions, rate limits, or whether the tool is read-only or destructive. The behavioral context is insufficient.

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 relatively short (two main sentences plus a code-like line). Key information (usage scenario and endpoint) is front-loaded, but the structure mixes natural language and code without clear separation. There is some room for improvement.

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 6 parameters, no output schema, and no annotations, the description should provide comprehensive guidance. It only gives the endpoint and a partial parameter hint. Return values, dependencies, and parameter constraints are missing, making it incomplete for effective use.

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

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

With 0% schema description coverage, the description should compensate. It only explains the 'lignes' parameter with a structure hint, leaving five parameters (notes, periode, collaborateur, date_emission, entreprise_nom) undocumented. This is inadequate for effective use.

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 'WHEN professional expenses need to be reimbursed or justified' and identifies the resource as 'Note de frais (app Frais)', which gives context but lacks a clear action verb like 'create' or 'submit'. It is not a tautology, but it is vague about the 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 begins with 'QUAND' (when) providing a usage scenario, but it does not specify when not to use this tool or mention alternative tools among the siblings. The guidance is implied rather than 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?

With no annotations, the description fully carries the behavioral burden and does so admirably. It discloses the free tier, 30-day unlimited access then 240 min/day, IP-based rate limiting, lack of email requirement, and that no API key is required to call this tool. This is rich, non-obvious behavioral context.

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

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

The description is longer than minimal but every sentence adds useful context. It is front-loaded with the most important 'call first' advice, then policy details. The use of ALL CAPS creates emphasis but slightly reduces readability; still, it is structured 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?

For a low-complexity tool with no output schema, the description covers the key context an agent needs: when to call, limitations, rate limits, and cost. It lacks an explicit statement of the response format, but the purpose of returning a key is strongly implied. Overall, it is sufficiently complete 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 coverage is 100%, so the description does not need to add much. It adds a small emphasis that email is not required, but this is already implied by the schema's optional flag. No additional parameter-level detail is provided beyond what the schema offers.

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's purpose: obtain a free API key immediately, with explicit guidance that it should be called first when no key exists. It distinguishes itself from sibling tools by being the key-provisioning tool and names the paid tools it enables.

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?

Explicit when-to-use guidance: 'QUAND vous n'avez pas encore de clé — APPELEZ-LE EN PREMIER'. It also explains that no email or existing key is needed, and positions the tool as a prerequisite for testing paid sibling tools, making the use case and alternatives 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?

With no annotations provided, the description carries the full burden. It discloses that the tool is free ('0 units, no API key') and specifies the HTTP method ('REST: GET'). This adds valuable behavioral context beyond the empty input schema, though it does not detail the return structure.

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, each essential. The first sentence front-loads the usage context, the second defines the tool, the third provides technical details. 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 simple, parameterless catalogue tool with no output schema, the description covers purpose, usage context, and technical endpoint. It lacks explicit description of the return format, but the naming and context ('catalogue... mapped to MCP tools') provide reasonable inference. Completeness is adequate.

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 0 parameters, so schema description coverage is trivially 100%. Baseline is 4 as per guidelines. The description adds no parameter-specific info (none needed), and the schema is self-explanatory.

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

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

The description clearly states it's a 'FREE catalogue of the Partner Portal apps' and tells the agent to call it first when helping artisans/BTP companies to know what the portal covers. It identifies the resource (catalogue) and action (calling it), and distinguishes from siblings by being a discovery 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?

The description explicitly says 'WHEN you are helping an artisan or a BTP company and need to know what the Partner Portal already covers — call it first.' This provides clear context on when to use the tool. It does not mention when not to use or alternatives, but the directive to 'call it first' implies it precedes other tools, which is sufficient.

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 provided, so description carries full burden. It discloses layout for window envelopes, address usage distinction, and validation rule (postal code). Does not mention side effects or authorization.

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?

Front-loaded with key condition and purpose. Includes legal reference, layout, and guardrail in a structured way. Slightly dense but each sentence adds value.

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?

Covers many behavior aspects and a validation rule. Lacks output format details (though mentions PDF via API). Does not explain all required fields; only emphasizes addresses. Moderate completeness given no output schema.

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 low (30%). Description adds meaning for 'locataire_adresse' vs 'logement_adresse' (postal vs property address, fallback). Other parameters (e.g., 'lieu', 'loyer') are not elaborated. Partial compensation.

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 it generates a rent receipt ('Génère une quittance de loyer') referencing the relevant law. It does not explicitly differentiate from siblings, but the verb+resource is specific.

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?

Clear when to use: after payment and tenant request ('QUAND le loyer a été PAYÉ... jamais avant encaissement'). Also mentions a guardrail (refusal if no 5-digit postal code). No explicit when-not or alternatives.

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 provided, so the description carries the full burden. While it describes the calculation, it does not disclose whether the tool modifies data (e.g., 'solder les provisions' implies a write), permissions required, or side effects. This lack of disclosure is a significant gap.

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 and front-loads the condition. It is informative but slightly verbose due to parentheses. Overall, it is efficient and clear.

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 6 parameters, no output schema, and no annotations, the description covers the purpose and calculation but lacks explicit return value details and side effects. It is moderately complete but could be more comprehensive.

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 only 17% schema description coverage, the description adds meaning by explaining key parameters (tantiemes, charges) and the calculation logic (pro rata temporis, lot shares). It partially compensates for the schema's lack of descriptions, though it does not detail all parameters.

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

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

The description clearly states the tool's purpose: annual charge regularization in property management, specifying when it is used (when charge exercise is closed) and what it computes (tenant share, pro rata, balance). It differentiates from siblings by focusing on charge settlement.

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 a clear condition for use ('QUAND l'exercice de charges est clos...'), but does not explicitly state when not to use it or suggest alternatives among siblings. It gives sufficient context for a specialized tool.

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 provided, so description must fully disclose behavior. It mentions 'reminder' and levels but does not explain what happens when invoked (e.g., sends email, generates document), leaving the agent uncertain about 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?

Description is concise with two focused sentences plus endpoint. Some redundancy in differentiating from relance_impaye, but overall well-structured 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 12 parameters, no output schema, and no annotations, the description is insufficient. It omits parameter meanings, typical usage patterns, and behavioral details, making it incomplete 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?

Schema has 12 parameters with 0% description coverage; description does not explain any parameter except a minor hint about 'niveau' (levels 1-4). The agent receives no guidance on what iban, delai, etc., represent.

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 it handles reminders for unpaid BTP client invoices, using specific verb 'relance' and distinguishes from sibling 'relance_impaye' which targets tenants.

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 states when to use (unpaid client invoices) and warns not to confuse with tenant reminders, providing clear context and 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?

No annotations provided, so the description carries the full burden. It discloses that from level 3, the notice engages legal procedure and mentions article 24. It also states output formats (HTML, PDF via POST). However, it omits details like side effects, required permissions, or whether it modifies state.

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 somewhat verbose and includes marketing language ('Démarchage : inciter le client à acheter le plan Agent Synergieloc.') that is not essential for tool selection. Key information is present but could be more 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 tool has 10 parameters and no output schema, the description is incomplete. It does not explain the purpose of most parameters, the format of the 'detail' array, or what the response contains beyond HTML/PDF. More detail is needed for an AI 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?

Only the 'niveau' parameter has a description (mapping to levels 1-5). The other 9 parameters (e.g., 'lieu', 'detail', 'montant_du') are not explained in the description. With only 10% schema description coverage, the description adds little value 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 it generates late rent reminders with levels 1-5, distinguishing from siblings like 'relance_facture_client' which handles invoice reminders. 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?

It explicitly says to use when rent is unpaid after due date and explains how to choose levels based on age. From level 3, it notes that a formal notice engages the procedure. However, it does not formally exclude other tools or provide exhaustive when-not-to-use guidance.

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