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

The annotation readOnlyHint already covers the safety profile, and the description adds useful context: output is Hebrew text with an English translation only if available, and the returned text is the authoritative basis for citations. It does not describe failure modes or the exact response structure, but for a read-only lookup this is an acceptable level of disclosure.

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 dense sentences covering purpose, examples, and the key quoting rule, with no filler. The purpose is front-loaded, and the examples are compactly listed.

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 one-parameter, read-only retrieval tool with 100% schema coverage, the description adequately covers what to pass, what to expect in the response, and how to use the result. The only minor gap is not describing the response encoding or invalid-reference behavior, but the tool's simplicity makes this non-critical.

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 ref as a Sefaria-format English reference, but the description adds five concrete reference examples, including complex ones like 'Mishneh Torah, Laws of Repentance 2:1'. These examples materially help an agent construct a valid argument.

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 'Texte d'une référence Sefaria' and gives concrete examples like 'Genesis 1:1', 'Berakhot 2a', and 'Shulchan Arukh, Orach Chayim 1:1', which make the resource and scope unambiguous. It lacks an explicit action verb such as 'returns' or 'retrieves', so it stops short of the highest clarity score.

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 instruction 'TOUJOURS citer depuis le texte réellement lu ici, jamais de mémoire' strongly implies this tool is the authoritative source for quoting Sefaria texts. However, it never contrasts this tool with siblings like sefaria_search or sefaria_links, so choosing among them is left mostly to inference.

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