l0g.fr Risk Intelligence

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description adds value by confirming determinism and listing output components (documents, claims, etc.). However, it does not disclose any additional behavioral traits like authorization needs or output size limits.

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, front-loading the key output components. Every sentence adds value, though a more structured format could improve scanability.

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 existence of an output schema and strong annotations, the description covers the tool's purpose and behavior adequately. It is missing explicit differentiation from siblings, but otherwise is complete for a deterministic research tool.

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

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

Schema coverage is 100%, so the schema already documents all parameters. The description does not add new semantic details beyond the schema; it only summarizes the pack contents. Baseline 3 is appropriate.

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

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

The description clearly states the tool composes a deterministic research pack with specified components and explicitly says it produces no investment opinion. However, it does not differentiate from sibling tools such as 'search_l0g' or 'discover_l0g', which may have overlapping functionality.

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 no explicit guidance on when to use this tool versus alternatives. It states the output (no investment opinion) but lacks conditions for use, prerequisites, or exclusions relative to 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?

Annotations already indicate readOnlyHint and idempotentHint, so the description adds value by specifying that the tool returns a compact overview covering capacities, versions, freshness, contracts, proof rules, and MCP paths. No contradiction with annotations.

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

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

The description is a single concise sentence in French, front-loading the key term 'compact entry point'. It is efficient, though clarity could be improved.

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 presence of an output schema and annotations, the description provides an overview of returned content but lacks detail on how it differs from sibling tools or the exact structure of the output. 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 100%, and the description does not add meaningful additional context beyond the schema's parameter description. The baseline of 3 applies.

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

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

The description states 'Point d’entrée compact' (compact entry point) and lists various aspects like capabilities, versions, freshness, etc., but does not clearly define a specific action or differentiate from siblings like search_l0g. The purpose is vaguely implied.

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. The phrase 'compact entry point' hints at a summary function, but no when-to-use or when-not-to-use instructions are 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?

Annotations already declare readOnly, idempotent, not destructive. The description adds valuable behavioral context: opaque pagination, explicit truncation, references, and canonical URL. No contradiction.

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

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

A single, efficient sentence that front-loads the action and covers key features without redundancy. Every word earns its place.

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

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

Given the output schema exists and annotations provide safety, the description covers pagination, truncation, references, and canonical URL. It doesn't explicitly mention that it returns the document content, but 'Lit' implies this. Nearly complete for a read-only 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?

With 100% schema coverage, baseline is 3. The description mentions pagination and truncation but does not add new meaning beyond what the schema parameters already describe. No elaboration on 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 verb (Lit) and the resource (article ou guide l0g par slug), and distinguishes from siblings by mentioning specific features like opaque pagination, explicit truncation, references, and canonical URL.

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 vs alternatives. It implies usage for reading documents by slug, but does not specify when not to use or when to prefer siblings like search_l0g or get_evidence.

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

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

Annotations already declare safe read-only, idempotent behavior. The description adds context about querying different evidence views, but doesn't introduce new 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?

Single sentence in French, front-loaded, no redundancy. Could be slightly more detailed but 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 full schema coverage, output schema, and annotations, the description adequately covers the tool's purpose. Short but 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?

Input schema provides 100% coverage with descriptions for all 9 parameters. The description does not add significant additional semantics 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 queries claims, sources, sub-graph, or source register, distinguishing it from sibling tools like search_l0g or get_document.

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 evidence retrieval but does not explicitly state when to use vs alternatives or 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?

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds context about returning a 'stable and sourced contract' and enumerates the modes (current, diff, history, replay), but does not go beyond what annotations and schema convey.

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 only two sentences, front-loading the primary role of the tool. Every phrase earns its place, with no redundant or superfluous 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's complexity (5 parameters, 4 modes), the description sufficiently covers its purpose and usage context. The existence of an output schema reduces the need to explain return values. The instruction to 'start here' provides clear entry point guidance.

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?

Although schema coverage is 100% with parameter descriptions, the description explains how parameters relate to modes (e.g., 'diff 1/7/30 jours' maps to window, 'historique d’un instrument' ties to instrument). This adds semantic value beyond the schema by contextualizing the parameters in 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 returns a 'stable and sourced contract' for various risk views (current state, diff, history, replay). It uses specific verbs and resources, and is distinct from sibling tools like get_document or search_l0g.

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 'Commencer ici pour toute question sur le risque' (Start here for any question about risk), indicating it is the primary tool for risk queries. It does not, however, explicitly exclude alternative tools or mention when not to use it.

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

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds behavioral context by specifying the result format (canonical URLs, bounded excerpts) and the bilingual filtering capability, which is valuable beyond the annotations. No contradiction with annotations.

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

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

Single sentence that is front-loaded with the core action and scope. Every word is informative and there is no redundancy or filler. Efficiently conveys the 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?

For a search tool with an output schema, the description adequately defines the resource scope and output format. The list of resource types ('articles, guides, glossaire, méthodologies et sources') is somewhat vague but sufficient. The output schema covers return values, so the description does not need to detail them. A slightly more precise scope statement would improve it further.

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?

All parameters have descriptions in the schema (100% coverage), so the description doesn't need to add much. It mentions 'bilingual' which is already covered by the language parameter. The description adds no new parameter-specific meaning beyond what the schema provides, meeting the baseline.

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 performs a filtered bilingual search across multiple resource types (articles, guides, glossary, methodologies, sources) and returns canonical URLs and bounded excerpts. This clearly distinguishes it from sibling tools like get_document which retrieves a specific document, or discover_l0g which likely has a different discovery 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 explicit guidance on when to use this search tool versus alternatives like get_document or get_evidence. The description implies it's for finding content, but does not state when not to use it or mention sibling tools as alternatives.

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