Search post-canonical texts

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

Annotations already declare readOnly, idempotent, destructive=false and openWorld=false, so safety is covered; the description adds genuine behavioral context beyond that: diacritics are optional, matching is conjunctive across all terms, quoted phrases are supported, results carry canonical: false, and it works offline. It does not describe result payload shape or pagination behavior, which keeps it below the top mark.

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 dense sentence plus two short clauses; the corpus scope is front-loaded, the parenthetical enumerates covered works, and every trailing clause (diacritics optional, all words must appear, phrases allowed, not the canon, offline) carries distinct operational value with 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?

For a read-only search tool with no output schema and a simple flat parameter set, the description covers scope, matching rules, and the key distinguishing label on results. The main residual gap is that it never says what a hit actually contains (text passage, reference, book id) nor that limit/offset paginate, which matters for a 5-parameter search endpoint.

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?

With schema coverage at only 40% (limit, offset and query have no schema descriptions), the description compensates by explaining query syntax in real detail — optional diacritics, AND-of-all-words, quoted phrases. The books and section filters are left to the schema's own enum and example descriptions, which is acceptable but leaves limit/offset entirely undocumented anywhere.

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 gives a specific verb and resource ("Search the full Pāli text of the post-canonical books") and enumerates the covered works (Visuddhimagga, Abhidhammatthasaṅgaha, Ṭīkā, VRI Añña). It explicitly draws the boundary against the canon corpus and against the sibling search_texts-style tools by noting results are labelled canonical: false.

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 clearly establishes the domain of use (post-canonical only, "Not the canon") and gives the matching semantics (all words must appear, quoted phrases allowed), which tells an agent when this tool will and won't find a hit. It stops short of naming the alternative tool to use for canonical search, so the routing is implied rather than explicit.

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