Browse topics

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 and offline profile is largely pre-covered; "Works offline" restates openWorldHint rather than adding new information. What the description does add is corpus provenance and size, but it says nothing about ordering, page size, or what a result row contains — the behaviors an agent actually needs for a paged browse call.

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?

Two short sentences with no filler, and the resource plus corpus scope is front-loaded before the offline note. Efficient, though the brevity comes at the cost of the missing pagination detail, so it reads as terse rather than fully earned.

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 zero required parameters, the description should at minimum convey what a topic entry looks like and how paging works; neither is present. Annotations and a partially documented schema carry the rest, so the definition is callable but leaves an agent guessing on result shape and page sizing for a 300+ item index.

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 only 50%: `index` and `query` are documented in the schema, while `limit` and `offset` have no descriptions anywhere. "Browse or search" loosely maps to the index/query split, but the description adds no pagination semantics — no default page size, no max-of-200 guidance, no offset behavior, no result ordering — which is exactly the gap a 50% coverage tool needs the description to fill.

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 pair (browse/search) over a named resource (the topic index) and quantifies the corpus at 300+ topics from Access to Insight's General and Numerical indexes, which distinguishes it from free-text tools like search_texts. It never names a sibling it competes with, so the separation from `topic` or `dhamma_list` is left to inference.

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?

"Browse or search" implies two modes of use, and "Works offline" hints at a no-network retrieval context, but there is no explicit when-to-use-this-instead-of guidance and no mention of the sibling tools that overlap most (topic, search_access_to_insight, dhamma_list). Usage is inferable rather than stated.

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