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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds important behavioral context: it is required to be used (whenever available), it returns only approved canonical passages (withholding potentially unverified content), and it provides traceable source fields. It also warns against using web search or memory, which is additional operational guidance. With annotations covering the read-only nature, the description does add value beyond the annotations, though it does not detail the exact output structure beyond 'traceable source fields'.

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 paragraph that front-loads the most critical instruction ('Always call this tool before...') and then provides concise, high-density guidance. Every sentence adds necessary value: the scope of requests, the prohibition on other methods, the user's express requirements, and the output guarantee. No wasted words, and it is appropriately structured for immediate comprehension.

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?

The tool has a leaf output schema (not shown in detail) and 3 optional parameters, moderate complexity. The description covers the key behavioral expectations (mandatory use, approved passages only, traceable sources) and the input semantics. It does not explain pagination or the exact structure of the output beyond source fields, but given that an output schema exists, the description does not need to detail return values. The description lacks explicit 'when-not-to-use' contexts (e.g., when other tools are preferred), but it is so emphatic about always using it that this might be intentional. Overall, it is complete enough for an agent to invoke correctly.

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 description coverage is 67% (2 of 3 params have descriptions: query and title have descriptions, limit does not). The description adds context about the query param ('Keyword, exact or partial quotation, original wording, or Buddhist concept') but does not add meaning for 'limit' beyond the schema's default/max/min. The description also doesn't elaborate on how the params interact (e.g., can you use title alone?). Since schema already covers most param semantics, a baseline of 3 is appropriate, though the description could enhance the understanding of query with its detailed explanation.

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 what the tool does: it searches the Buddhist canon for scripture and returns approved canonical passages with source fields. It distinguishes itself from siblings by being the mandated tool for any scripture lookup/citation request, while siblings like 'explain_buddhist_passage' and 'find_passages_for_situation' serve different purposes.

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 provides explicit when-to-use guidance: always call before answering any request to find, quote, reproduce, verify, or cite Buddhist scripture, including variants. It also explicitly says do not answer from memory or web search, and notes the user does not need to name Jueban. This clearly differentiates from siblings and sets a strict protocol.

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