public-tools

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

With no annotations, the burden falls on the description. It explains the computation and legal basis but does not disclose side effects or constraints beyond jurisdiction. It is adequate but not detailed.

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 sentences, front-loaded with the main action, followed by a French translation for clarity. No superfluous information.

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

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

Given the complexity and lack of output schema, the description adequately lists the expected results (cap, deadline, retentions, penalty). It is sufficient for an agent to understand the tool's return.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds context about the legal article and outputs, but does not add significant meaning beyond the schema's parameter 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 identifies the verb 'compute' and the resource 'security deposit restitution' with specific outputs (legal cap, deadline, retentions, penalty). It references the legal article, differentiating from sibling tools like 'generate_bordereau_restitution' which is about document generation.

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?

While the purpose is clear, the description lacks explicit guidance on when to use this tool versus alternatives. No when-not or comparison with siblings (e.g., generate_bordereau_restitution) is provided.

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

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

No annotations provided, so description carries full burden. It discloses that the tool geocodes an address and returns an 'indicative summary' plus a link, indicating non-authoritative output. Does not mention destructive effects or rate limits, but appropriate for a read-only lookup 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?

Description is two sentences: first defines action and output, second provides purpose. Efficient and front-loaded, though second sentence phrasing ('For the lease's...') is slightly fragmented.

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

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

For a simple tool with one fully-documented parameter, the description covers input, output (summary + link), and legal context. No output schema needed given clear description of return value.

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 one parameter 'address' with 100% schema coverage. Schema already provides type and example. Description adds no additional semantic value beyond what is in 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?

Description explicitly states the verb (geocode/return), resource (address risks), and legal context (lease mandatory risk annex). Title and description clearly differentiate from sibling tools which are document generation or simulation tasks.

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?

Description provides clear context: 'For the lease's mandatory risk annex.' It implies when to use this tool (when preparing a rental risk disclosure). No explicit exclusion or alternative tools mentioned, but sibling tool names clearly indicate different purposes.

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 disclose behavior. It states the tool returns reference rent, upper ceiling, and verdict, implying read-only verification. However, it does not explicitly confirm non-destructiveness, authorization needs, or rate limits. Adequate but minimal.

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 sentences plus a short 'Use for' line. Front-loaded with main purpose. Bilingual but efficient. No unnecessary words. 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?

The description mentions return values (reference rent, upper ceiling, verdict) but lacks details on output structure (e.g., whether verdict is a string or boolean). For a tool with 7 parameters and no output schema, more specificity would help an agent understand the response format. Adequate but not fully complete.

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

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

Schema has 100% coverage with French descriptions for all 7 parameters. The description adds no extra meaning beyond the schema. Baseline 3 is appropriate.

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

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

Description clearly states the tool checks rent control compliance, returning reference rent, upper ceiling, and verdict. It specifies use cases (max allowed rent, rent cap, is city rent-controlled) and distinguishes itself from sibling 'get_reference_rent' by including a verdict. Bilingual with specific verb and resource.

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

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

Explicitly lists use cases: 'max allowed rent, rent cap, is a city rent-controlled.' Provides direct guidance on when to use. Does not mention when not to use or alternatives like 'get_reference_rent', but the context is clear enough.

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 the link validity (30 minutes) and that the signature is legally binding. However, it does not mention if the draft is persisted, authentication required, or error behavior. This is moderate 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 two sentences plus a short French note. It is front-loaded with the purpose and efficiently covers key points (creation, link, signature) without 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 the complexity of creating a legal document and no output schema, the description could explain more about the return link's usage, error cases, or data validation. It covers basics but leaves gaps for a complex tool.

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

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

Schema coverage is 100% but each parameter is an object with additionalProperties true and only example structures in descriptions. The descriptions add meaning by providing field examples (e.g., rent_amount, charges_amount) that are not in the schema. This significantly aids understanding despite the schema's minimalism.

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 French residential lease draft and returns a link for finalization and e-signing. It includes synonyms in French, and the purpose is distinct from sibling tools like generate_avenant or generate_conge which handle modifications or terminations.

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 'Use whenever a user wants to create, draft or generate a lease / rental contract.' This gives clear context, though it does not list alternatives or when not to use. However, sibling names imply use cases, so it is still helpful.

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

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

The description reveals it returns a link to view/download the PDF, which is useful behavioral info. However, since no annotations are provided, it does not disclose side effects (e.g., whether it creates a stored record) or authorization needs. It is moderately transparent.

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 two English sentences and one French sentence. It includes the key fields and output behavior. No unnecessary words, though the French line could be considered redundant for an English description.

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 minimal schema and no output schema, the description adequately explains the input fields and output (link to PDF). However, it lacks details on response format (e.g., JSON structure) and prerequisites for 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?

The input schema has a vague 'payload' parameter with additionalProperties: true. The description compensates by listing the expected fields (landlord_name, tenant_name, property_address, object, effective_date). This adds critical meaning 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 a lease amendment (avenant) and produces a PDF link. The title reinforces the purpose. Among sibling tools, it is distinct as the only one generating a lease amendment, so purpose is 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?

There is no guidance on when to use this tool versus alternatives like create_lease_draft or generate_resiliation_amiable. The description only states what it does, not context or selection criteria.

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

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

The description reveals that the tool returns a link to view/download the PDF (output behavior), but does not discuss side effects, authentication, rate limits, or error handling. With no annotations, this is basic but incomplete.

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

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

The description is concise and front-loaded, covering purpose, fields, and output in three short sentences. Every sentence adds useful information, including bilingual context.

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?

Adequate for basic use: explains purpose, fields, and output format. However, it lacks specification of which fields are required, value formats, or error conditions. For a document generation tool, more detail on field constraints would improve completeness.

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

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

The schema only defines a generic 'payload' object. The description adds value by listing the expected fields (landlord_name, tenant_name, property_address, deposit_amount, retentions), compensating for the schema's lack of detail.

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 a security-deposit restitution slip (PDF) and lists the fields. It is distinguishable from sibling tools like calculate_deposit_restitution, but does not explicitly contrast with other generate_* documents.

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

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

No guidance on when to use this tool versus alternatives like calculate_deposit_restitution or other generate_* tools. No prerequisites or context provided.

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

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

The description discloses that the tool returns a link to display/download the PDF, providing some behavioral insight. With no annotations, the description should cover more behavioral traits (e.g., side effects, permissions, storage), but it lacks those details.

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 (English + French), concisely listing fields and output type. It is front-loaded and wastes no words, though a more structured format (e.g., bullet list) could improve readability.

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 explains the tool's purpose, required fields, and output (link to PDF). However, it omits details about link behavior (e.g., expiration), error handling, authentication requirements, and whether additional payload properties are allowed. Given the complexity (no output schema, single nested param), more completeness is needed.

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 contains only a generic 'payload' object with no property definitions. The description compensates by listing the six fields (guarantor_name, tenant_name, landlord_name, property_address, rent, duration), which is essential for correct usage. This adds significant semantic 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 'Generate[s] a guarantor's guarantee deed' and lists the fields, indicating a specific PDF generation task. The French translation aids clarity. However, it does not explicitly differentiate from sibling tools, though the uniqueness of 'cautionnement' suggests distinct purpose.

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

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

No guidance is provided on when to use this tool versus alternatives. The description does not mention prerequisites, context for use, or scenarios where other tools (e.g., generate_avenant) would be more appropriate.

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

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

No annotations are provided, so the description must fully disclose behavioral traits. It mentions returning a link to view/download the PDF, but does not describe side effects, authentication needs, error conditions, or what happens if required fields (if any) are missing. The output behavior is partially covered, but significant gaps remain.

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

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

The description is very concise, with two short sentences (one in English, one in French) that immediately state the purpose and output. Every word is informative, and there is no redundant or irrelevant content.

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 a single optional object parameter, no output schema, and no annotations, the description is adequate for a simple PDF generation task. It specifies the decree reference and that few fields are needed. However, it lacks details on the payload structure and what constitutes 'few fields,' which could lead to incorrect usage. The completion is minimal but sufficient for a basic understanding.

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

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

The only parameter 'payload' is a generic object with a description that points back to the tool description. The tool description says 'few or no fields required' but does not list specific fields or structure. Schema coverage is 100% due to the parameter description, but that description adds no semantic value beyond what is already in the description. The description fails to compensate for the lack of parameter detail.

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?

Title and description clearly state the tool generates a recoverable charges list PDF, referencing the specific decree 87-713. The verb 'generate' and resource 'recoverable charges list' are unambiguous, and it distinguishes itself 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 notes 'few or no fields required' and references a French decree, which implies the tool is for creating this specific document. However, it does not explicitly state when to use it versus alternatives (e.g., other generate_* tools) or provide exclusions. Usage guidance is implied but not explicit.

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

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

No annotations are provided, so the description carries the full burden. It mentions generating a PDF and returning a link, but lacks details on destructive nature, authentication requirements, rate limits, or side effects. For a legal document tool, more behavioral context is needed.

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 two sentences and a French note, front-loading the main action. It is efficient but could benefit from more structure, such as sections for when to use and output details.

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

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

The description covers the basic purpose and fields, but lacks information on link validity, authentication, and legal context. Given the complexity of generating a legal document, more completeness is desirable.

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 a single generic payload object with 100% coverage relying on the description. The description lists the specific fields (landlord_name, tenant_name, etc.), adding significant meaning beyond the schema's vague property 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 generates a notice-to-quit letter for landlord or tenant, lists specific fields, and mentions the output is a PDF link. It distinguishes from siblings by specifying the exact document type and includes French terminology for clarity.

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

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

The description does not provide guidance on when to use this tool versus alternatives such as generate_resiliation_amiable or generate_notice_information. No explicit context for usage, prerequisites, or exclusions 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 the burden. It discloses that the output is a link to display/download PDF and that the report is semi-filled (print-and-complete). However, it omits details like authorization requirements, whether the link expires, or if any data is stored.

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 short and front-loaded with the core action and output. The French sentence is somewhat redundant but not harmful. Could be slightly more concise by merging the French into the English.

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

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

Given no output schema, the description explains the return value (link to PDF). It covers the key aspects: input fields, semi-filled nature, decree reference, and output format. However, it doesn't mention link expiration or file size, which could 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 only defines 'payload' with no properties, so the description adds critical value by listing the expected fields (landlord_name, property_type, etc.). This compensates for the schema's lack of detail, though types and constraints are still absent.

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?

Clearly states it generates a semi-filled inventory report (PDF) referencing a specific decree (decret 2016-382) and lists the included fields. This distinguishes it from sibling tools like generate_inventaire_mobilier, which serve different document types.

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

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

No explicit guidance on when to use this tool versus alternatives. It describes what the tool does but does not specify context, prerequisites, or when to avoid 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?

No annotations provided, so description must cover behavioral traits. It mentions returning a PDF link, but fails to disclose side effects, authentication needs, or behavior with empty payload.

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 short and front-loaded, but lacks structure. It combines purpose, language hint, and output in a run-on manner. Could be more organized without being longer.

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

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

No output schema exists, so description must explain return values; it does mention a link. However, it fails to describe the critical payload parameter's structure, leaving the agent without guidance on what to provide.

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 sole parameter 'payload' is described as an object with 'additionalProperties: true' and no defined properties. The description says 'Few or no fields required' but does not specify what fields are accepted, adding no 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 'Generate a wear-and-tear (vetuste) grid' and mentions the output is a PDF link. It distinguishes itself from siblings by naming the specific document type in both English and French.

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

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

No guidance on when to use this tool versus sibling generate tools. Only notes 'Few or no fields required,' which is insufficient for an agent to decide contextually.

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 must disclose behavioral traits. It mentions returning a link for PDF access but does not confirm whether the operation is read-only or has side effects. The generation action hints at mutation, but safety profile is 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 with three short sentences covering purpose, fields, and output format. Every sentence adds value, and key information is front-loaded.

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

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

The description adequately covers the payload fields and output (link). However, it omits details on payload structure, optional/required keys, and any constraints. Given the simple schema, more detail would help an agent use the tool correctly.

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

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

The schema only defines a generic 'payload' object with no properties. The description compensates by listing example fields (property_address, rooms/items), adding context beyond the schema. However, it lacks detailed structure or optional field 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 clearly states the verb 'generate' and the resource 'furniture inventory PDF' for furnished leases. It distinguishes from sibling tools like generate_etat_des_lieux by specifying the document type 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 implies this tool is for furniture inventories in furnished leases, providing clear context. However, it does not explicitly state when not to use it or compare to alternatives, missing an opportunity for direct guidance.

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

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

With no annotations, the description must disclose behavioral traits. It states the output is a link to a PDF, but it does not clarify whether this tool is read-only (it likely creates a document server-side), what side effects exist, or if authentication/permissions are required. The description is insufficient for full behavioral understanding.

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

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

The description is extremely concise—two sentences plus a French line—with no superfluous words. It front-loads the primary purpose and output format.

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 a single parameter with a nested object and no output schema, the description barely covers what the payload should contain beyond one field. It does not explain error cases, link behavior, or how to handle the output. Compared to the richness of sibling tools, this 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?

The input schema has one parameter 'payload' with a generic description pointing to the tool description. The description adds the hint 'Fields: lease_type', which provides more meaning than the schema alone. However, it does not specify whether lease_type is required, its possible values, or any other expected fields, leaving 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 it generates the mandatory information notice (loi ALUR) and returns a PDF link. The verb 'generate' and resource 'notice_information' are specific, but it does not explicitly distinguish from sibling tools like generate_avenant or generate_conge, which are also PDF generation tools for leases.

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

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

No guidance on when to use this tool versus alternatives (e.g., create_lease_draft or other generate_* tools). The description gives no context about prerequisites or situations where this tool should or should not be used.

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 return value (link to PDF) and mentions partial-payment support, but with no annotations it omits side effects, auth needs, or rate limits. Adequate but basic.

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?

Short and front-loaded with purpose, then fields, then return info. Could list fields more structuredly but overall 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?

With no output schema, description explains the PDF link return. Lists all needed fields and mentions partial receipt. Adequate for a simple generation tool given sibling context.

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

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

Schema coverage is 100% but payload description is generic; the tool description compensates by listing field names and providing an example month, adding meaning 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?

Clearly states it generates a rent receipt (quittance de loyer) as a PDF, explicitly distinguishes from sibling tools by specifying the document type and listing required fields.

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?

Implies use for generating rent receipts, no explicit exclusions or alternatives needed as no sibling tool does the same. Context is clear but lacks explicit 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.

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 PDF and returns a link to view/download. It does not detail nondestructive behavior, authentication, or error handling, but for a document generation tool this is acceptable.

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 (two sentences plus field listing) and front-loaded. It includes both English and French explanations. Could be more structured, but it is 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 tool's simplicity (one nested parameter, no output schema), the description is fairly complete: it specifies the document, required fields, and output format (PDF link). It does not mention error scenarios, but for a straightforward generation 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?

The input schema has one opaque 'payload' object with additionalProperties: true. The description compensates by listing the expected fields (landlord_name, tenant_name, property_address, amount_due, period). This adds meaning beyond the schema's vague description.

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 an unpaid-rent reminder letter (PDF). It lists key fields (landlord_name, tenant_name, etc.) and mentions both English and French names. This distinguishes it 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 implies use when needing an unpaid-rent reminder, but does not explicitly state when to use or avoid this tool versus alternatives. Sibling tool names indicate different documents, so context is provided indirectly.

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 burden. It discloses that the tool returns a link to view/download the PDF and that few fields are required. However, it does not mention safety traits (e.g., read-only), side effects, or permissions, which is a moderate gap given the absence of 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 very short (three sentences) and no wasted text. However, the mix of English and French may reduce clarity for non-French-speaking agents. The first sentence front-loads the core purpose, which is good.

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

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

Given the tool's flexible input (payload with no defined properties) and the presence of many similar sibling tools, the description lacks completeness. It does not specify required fields or provide examples, which is critical for an agent to use it correctly. The reference to the decree is helpful but insufficient for full 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 has one parameter `payload` described only as an object to see the tool description for fields. The tool description does not list any specific fields, saying only 'few fields required'. Schema coverage is 100% for the top-level property, but the description fails to add meaningful detail about payload structure, leaving the agent without necessary guidance for input.

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 it generates the list of repairs chargeable to the tenant, referencing a specific decree (decret 87-712). It clearly distinguishes from siblings like `generate_charges_recuperables` by focusing on tenant repairs for a defined legal context. The output as a PDF link is also mentioned.

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 notes 'Few or no fields required' which hints at ease of use, but there is no explicit guidance on when to use this tool versus alternatives like `generate_etat_des_lieux` or `generate_charges_recuperables`. The purpose implies usage for tenant repair lists, but no exclusion or alternative comparison is provided.

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

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

No annotations provided. The description explains it returns a link to view/download the PDF, but does not disclose side effects, authentication needs, or whether it's destructive. With no annotations, the description partially compensates but leaves gaps.

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 with two sentences plus a French note. Front-loaded with purpose. Could be improved by structuring fields as a list 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?

Adequate for a simple document generation tool. Lacks output schema but describes return format (link to PDF). Could mention date format requirements or contrast with sibling generate_conge.

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

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

The schema has a generic 'payload' object with no specific fields, but the description lists the four key fields (landlord_name, tenant_name, property_address, end_date), adding meaning. However, payload allows additional properties not documented, creating 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 title and description clearly state it generates a mutual lease termination PDF. It specifies the key fields (landlord_name, tenant_name, property_address, end_date). Distinct from siblings like generate_conge (unilateral notice) and generate_avenant (amendment).

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?

Implies usage for mutual termination but does not explicitly state when to use this tool versus alternatives like generate_conge. No prerequisites or exclusions provided.

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

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

No annotations are provided, so the description carries the full burden. 'Return' implies a read operation, but no explicit statement about side effects, authentication needs, or rate limits. It adequately states what is returned but lacks depth.

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. The first effectively front-loads purpose and inputs. The second clarifies the quarter concept and provides French translation. No redundancy, but could be slightly 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?

For a simple retrieval tool with no output schema, the description covers key output fields (reference rent, bounds, freshness) and all required inputs. Missing details like error behavior or output format, but adequate given the tool's simplicity.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds minor context (e.g., 'EUR/m2' for output, 'rent-controlled zone' for quarter) but does not significantly enhance meaning beyond the schema's parameter 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 returns reference rent with bounds and freshness for a quarter, by specific criteria. It uses specific verb ('Return') and resource, but does not explicitly distinguish from the sibling tool 'check_rent_control' which may also relate to rent control.

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

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

No guidance on when to use this tool versus alternatives. The sibling list includes 'check_rent_control' which is semantically related, but the description provides no comparison or conditional usage 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 must bear full burden. It discloses that it is a simulation and returns new rent, % change, and increases, but does not explicitly state it is read-only, non-destructive, or any authorization needs. For a compute-only tool, this is adequate but not thorough.

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 two sentences, one English and one French, covering purpose and outputs. No waste, though the French sentence is slightly redundant but adds multilingual accessibility.

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

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

Given no output schema, the description adequately details the return values (new rent, % change, monthly/annual increase) and references the legal article. It does not cover error handling or validation, but for a straightforward calculation tool, it is mostly complete.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds context by explaining the tool uses two IRL index values for annual indexation and what it returns, but does not deepen understanding of individual parameters 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 computes revised rent after annual indexation using two IRL index values, referencing French law. It specifies the outputs (new rent, % change, monthly/annual increase), making the purpose distinct from siblings like simulate_irl_by_quarters.

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

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

The description implies usage for French rent revision (annual indexation) but does not explicitly state when to use this tool over alternatives like simulate_irl_by_quarters, nor does it provide when-not or context for exclusion.

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 full burden. It mentions automatic resolution of official values but does not disclose potential side effects, required permissions, error behavior (e.g., if values cannot be resolved), or whether the simulation is non-destructive.

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 sentences, one focused on functionality and one on usage guidance. No fluff, key information is front-loaded. Bilingual note adds value for French-speaking users.

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

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

Given no output schema, the description should hint at what the tool returns (e.g., new rent amount, IRL values used). It does not. Also lacks error handling info. For a simple simulation tool, more context is needed.

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

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

Schema description coverage is 100%, so baseline is 3. The description rephrases parameters (rent, two quarters, region) but adds no additional meaning or format details beyond what the schema 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?

Clearly states it simulates rent revision using IRL values with automatic resolution by the server. Distinguishes itself from sibling 'simulate_irl' by noting that the server resolves official INSEE values, and advises to prefer this when exact IRL values are unknown.

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 advises to prefer this tool when exact IRL values are unknown, contrasting with the sibling tool that likely requires manual IRL input. However, lacks explicit 'when not to use' or alternative scenarios.

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 the computations performed (yield, cashflow, tax regime) but does not mention side effects, authorization needs, or limitations. For a stateless computation tool, this is adequate but not fully transparent.

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 two sentences plus a keyword line in French, which is concise and includes relevant French terms. Could be slightly more structured, but 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?

The description outlines the outputs (gross/net yield, cashflow, recommended tax regime) despite no output schema. It provides sufficient context for a simulation tool, though specific output format is not detailed.

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

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

Schema description coverage is 100%, so the schema already documents each parameter. The description adds overall context but does not elaborate on parameter meanings beyond what the schema provides. Baseline of 3 is appropriate.

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

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

Description clearly states the verb 'Compute' and the resources: gross/net rental yield, cashflow, and recommended tax regime. It distinguishes from siblings as none of the sibling tools perform yield simulation.

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

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

The description implies usage for computing rental yields and tax regime recommendations but does not provide explicit guidance on when to use this tool versus alternatives. No exclusion conditions or prerequisites are mentioned.

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