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

Annotations already declare the tool read-only and idempotent, so the description does not need to repeat safety behavior. It adds useful behavioral detail by promising to detect 'every' citation and by stating that it returns matched spans and canonical references, which is beyond what the annotations or schema reveal.

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 action, and every clause adds value: examples clarify scope and the last sentence states the return shape. There is no filler or repetition of schema/annotation 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?

With no output schema, the description appropriately discloses that the tool returns matched spans and canonical references. It could be more explicit about behavior when no references are found or about the exact form of spans, but given the read-only, idempotent annotations and clear input examples, the description is largely 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 text and title parameters already have schema descriptions, and language is an enum, so the schema carries most of the param-semantics burden. The description's examples clarify what kinds of citations the text parameter may contain, but it does not add guidance on the title or language 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 names a specific action ('Scan free text... detect every citation'), a specific resource ('Jewish source'), and gives concrete examples like 'Genesis 1:1' and 'Berakhot 2a'. This clearly distinguishes it from siblings such as parse_reference, which would handle a single reference rather than scanning for all citations.

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?

It provides clear context for when to use the tool: free-text documents such as a dvar Torah, article, or shiur notes. It does not explicitly name alternatives or say when not to use it, but the intended use case is evident and no exclusions are needed.

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