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

Annotations already declare readOnly/openWorld=false, so safety carries little burden. The description adds real behavioral context beyond them: the tool either succeeds to a canonical ref or returns suggested completions, disclosing a partial-success mode an agent must be prepared to handle.

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 front-loaded sentence with the examples placed where they help most and no filler. Nothing is repeated from the schema or the title.

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 lookup with no output schema, the description covers the essential return behavior (canonical ref vs. suggestions). Slightly thin on what the agent should do after receiving suggestions, which matters because there is no output schema to clarify the shape.

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?

Only one parameter and schema coverage is 100%, so the schema already documents `query` fully. The parenthetical examples ('Rambam Teshuvah 2', 'Hilchot Shabbat ch. 5') add useful form guidance about what a valid reference looks like, but no detail on ambiguity, transliteration, or abbreviation handling.

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?

Specific verb+resource: turns a natural-language reference into the library's canonical ref, with two concrete examples that make the input shape unambiguous. It is clearly distinct from fetch_text/fetch_commentary by name, but it never explicitly contrasts itself with semantic_search, which is the closest sibling in intent.

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?

Usage is implied rather than stated: the agent can infer this is the normalization step before a fetch, and that unresolved input yields suggestions. There is no explicit 'use this when X, use semantic_search when Y', and no guidance on what to do with the suggested completions.

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