Texts on a topic

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior. The description still adds real value by stating it works offline and by enumerating the returned fields (canon ID, title, PTS page), but it says nothing about what happens with an unrecognized topic name (empty result vs. error).

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 tight sentence that leads with what the tool returns and follows with source and output fields. No filler; only the lack of an explicit usage clause keeps it from being maximally efficient.

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, the description correctly compensates by naming the returned fields and the offline behavior. For a one-parameter read-only lookup, the only mild gap is undefined behavior for unknown topic names.

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 100% and the single parameter already carries examples of its own. The description contributes the useful constraint that names correspond to Access to Insight's subject and numerical indexes, but repeats the same example style the schema already provides.

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 names the resource (texts) and the precise index it draws from (Access to Insight's subject and numerical indexes), plus the fields returned (canon ID, title, PTS page). It is clearly distinct from lookup-style siblings such as list_topics or lookup_pali, though it opens with a noun phrase rather than a verb.

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 examples of valid topic strings imply when to reach for this tool (topic-driven browsing), but there is no explicit statement about when to use it versus search_texts, list_topics, or browse_canon. An agent must infer the routing from the index reference alone.

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