Search the Tipiṭaka

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely behavioral context beyond that: works offline, results are labelled (expanded_from_english, canonical: false), post-canonical results are returned separately, and include_post_canonical is ignored when collection is set. It does not mention result ordering, pagination behavior, or how many hits are available in total.

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 search scope and query-syntax essentials are front-loaded in the first clause, and every later sentence carries new information about transliteration, English expansion or script. It is dense with parentheticals and semicolon-chained clauses, which costs some scannability, but there is no filler.

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 and seven parameters, the description covers the query contract, script handling, English expansion and post-canonical scope thoroughly enough to call the tool correctly. The remaining gaps are pagination (limit/offset) semantics and collection identifier details, which are moderate rather than blocking.

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 coverage is 57%, and the description compensates well for the undocumented parameters by explaining query syntax (diacritics optional, AND semantics, quoted phrases, transliteration schemes accepted), the effect of script on titles and excerpts, and the english expansion labels. It adds little for limit, offset, and collection beyond what the schema already says, so it is good but not exhaustive.

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?

States a specific verb+resource: searching the full Pāli text of the Tipiṭaka, plus text titles and English translation titles. It also implicitly separates itself from lookup_pali (single-word lexical lookup) and the Access to Insight siblings by naming the canon-wide corpus and its offline scope, so an agent can distinguish it from its siblings.

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?

Gives concrete usage context: diacritics optional, all words must appear, quoted phrases allowed, English queries expanded into Pāli, and collection/include_post_canonical narrowing. It stops short of explicit routing guidance such as "use search_post_canonical for the Visuddhimagga" or "use browse_canon to list texts without a query", so the agent must infer when a sibling is preferable.

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