Semantic search across fojin's Buddhist corpus (10K+ texts, 30+ langs).
Returns the most relevant passages, each with a `urn`, title, snippet and
similarity score. `lang` optionally filters by language code
(lzh=Classical Chinese, pi=Pali, sa=Sanskrit, bo=Tibetan, en=English).
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | ||
| limit | No | ||
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It does state what the tool returns and how `lang` filters results, but it does not explicitly say whether the operation is read-only, whether it has side effects, or whether authentication/rate limits apply. 'Semantic search' and 'Returns...' imply a safe read operation, but the lack of overt safety statements keeps this at a mid score.
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 compact and front-loaded. The first sentence states the tool's core purpose and corpus scope. The second sentence explains return values and language filtering in a tight, useful manner. No filler or repetition; every sentence adds value.
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 moderate complexity (3 params, no output schema, no annotations), the description covers the main essentials: purpose, scope, result format, and a key parameter. It omits result limiting behavior and does not discuss when not to use it, but it is still reasonably complete for a search tool.
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 has zero description coverage, so the description must compensate. It does explain `lang` with concrete language codes, and `query` is obvious from the 'search' wording. However, the `limit` parameter is not mentioned at all, leaving its behavior (control result count) undocumented. Partial compensation for the missing schema descriptions.
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 a specific verb and resource: 'Semantic search across fojin's Buddhist corpus'. It clearly distinguishes itself from sibling lookup tools by emphasizing corpus-wide semantic retrieval. The expected return (passages with urn, title, snippet, score) further clarifies its purpose.
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 this tool is appropriate: when you need semantic, content-based search across the whole corpus rather than exact lookups. It does not explicitly mention alternatives or exclusion criteria, but the context is clear enough for an agent to choose it over exact-match or entity-lookup tools.
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 targets a distinct resource or operation: commentaries for historical glosses, get_parallels for cross-tradition alignments, lookup_dictionary for terms, lookup_entity for entities, read_passage for full text, resolve_urn for citation resolution, search_corpus for semantic search, and verify_quote for verbatim verification. There is no overlap in purpose, and the boundaries are clear even between similar-looking lookups.
Most tool names follow a consistent verb_noun snake_case pattern (get_parallels, lookup_dictionary, read_passage, resolve_urn, search_corpus, verify_quote). The lone exception is 'commentaries,' which is a noun rather than a verb_noun construction, but this is a minor deviation in an otherwise uniform set.
With 8 tools, this server is well-scoped for a specialized Buddhist canon research domain. Each tool earns its place, covering search, retrieval, verification, lookup, and cross-reference without redundancy or bloat.
The toolset covers the complete research workflow: finding passages (search_corpus), reading them (read_passage), verifying quotes (verify_quote), resolving citations (resolve_urn), understanding terms (lookup_dictionary) and entities (lookup_entity), and exploring cross-tradition parallels (get_parallels) and commentaries (commentaries). No significant gaps exist for the stated purpose.