sefaria_linksCommentaires et textes liés à une référence (Rachi, Tossafot, midrachim, halakha, responsa…). Renvoie les réfs liées par catégorie — charger ensuite le texte voulu avec sefaria_text.
| Name | Required | Description | Default |
|---|---|---|---|
| ref | Yes | Référence source. | |
| category | No | Filtre optionnel : Commentary, Midrash, Halakhah, Responsa, Talmud… |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already signals a safe read operation, lowering the burden on the description. The description adds valuable behavioral context: it returns only linked references by category, not the full text, and directs the user to a subsequent sefaria_text call. This clarifies the tool's output scope beyond what annotations provide.
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, front-loaded sentence that packs essential information: what the tool does, examples of content types, the output format, and the next-step tool. Every clause earns its place with no filler or redundant repetition of the schema.
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 low complexity, read-only annotation, and rich schema, the description is largely complete: it states the input (reference), optional filter (category), output (linked refs by category), and a follow-up action. It does not detail exact response structure, but for this simple lookup tool the guidance 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 coverage is 100%, so parameters are already documented. The description adds semantics by giving concrete examples of category values (Rachi, Tossafot, midrachim, halakha, responsa) and explaining that results are grouped by category. This enriches the meaning of the optional 'category' parameter and the output structure.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Renvoie') and clearly identifies the resource: linked commentaries and texts for a Sefaria reference. It distinguishes itself from siblings like sefaria_text by stating it returns linked refs by category, not the text itself, and even points to sefaria_text for loading content.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use the tool: when you need commentaries or linked texts for a reference. It also gives workflow guidance by stating 'charger ensuite le texte voulu avec sefaria_text', indicating this tool is the first step before fetching full text. It does not explicitly mention exclusions or alternatives, 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.
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.