fiche_sourceCompose une fiche source prête à partager (WhatsApp/message) pour une référence : texte hébreu, traduction, référence exacte et liens d'étude. Le texte est réellement lu via Sefaria — jamais de citation de mémoire.
| Name | Required | Description | Default |
|---|---|---|---|
| ref | Yes | Référence Sefaria (ex : "Berakhot 2a", "Genesis 1:1", "Pirkei Avot 1:14"). | |
| segments | No | Nombre max de segments de texte à inclure (défaut 3). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds a key behavioral trait: the text is actually read via Sefaria, never cited from memory, which is important for reliability and freshness. This goes beyond the readOnlyHint annotation (which only indicates safety) by disclosing the data source and accuracy guarantee. 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?
The description is two sentences, front-loaded with the main function and purpose. The second sentence adds valuable transparency about data sourcing 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?
With 2 params, full schema coverage, and a clear description, the tool is well-specified. The description also lists the output contents (text, translation, reference, links), which compensates for the lack of an output schema. A bit more detail on output format would be nice but is not essential.
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 covers 100% of the parameters, with 'ref' providing a Sefaria reference example and 'segments' explaining the maximum number of text segments. The description adds no extra parameter-level detail beyond the schema, so the 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?
The description clearly states the tool composes a shareable source card ('fiche source') for a reference, including Hebrew text, translation, exact reference, and study links. The specific verb 'Compose' and the resource ('source card') make the purpose unambiguous. It is distinguished from sibling tools like sefaria_text by emphasizing the 'ready to share' formatting.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context: when the user needs a ready-to-share source card for WhatsApp/messaging, with translation and study links. It does not explicitly mention alternative tools or exclusions, but the context is clear. A slight gap remains in not naming when to prefer siblings like sefaria_text or sefaria_links.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool serves a clearly distinct purpose: skill loading, calendar, related links, full-text search, and text retrieval. There is no overlap in functionality, making selection unambiguous.
Four of five tools follow the 'sefaria_' prefix pattern, while 'hebrewbooks_skill' deviates slightly. The naming is still predictable and readable, with only minor inconsistency.
Five tools is well-scoped for a Torah study server, covering the essential operations without bloat. Each tool earns its place.
The set covers text retrieval, search, related texts, and daily study schedules, addressing the core domain. Minor gaps exist (e.g., no direct copy/export), but the workflow is functional.