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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered; the description adds genuinely new behavior: output is plain text, includes URL/dates/editing tool, and long records are returned in character windows paginated by next_offset. It stops short of documenting truncation/error behavior or limits beyond the schema's max_chars.

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 tight sentences, front-loaded with what is returned, then the pagination workflow. No filler and no restatement of the title.

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 carries the return-value burden and does so by naming the text, URL, dates, native_tool and next_offset. The main remaining gap is failure modes (invalid or outdated id) and how the windowing interacts with max_chars.

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 description coverage is 100%, so each parameter including around's override of offset is already documented. The description reinforces the around/offset workflow with snippet words and introduces next_offset as the continuation signal, but adds little semantics the schema does not already carry.

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 and resource (read one raq_search result in full as plain text) and names the return payload (URL, dates, native_tool). It also anchors itself to siblings by tying input to raq_search and pointing edits at the module tool, so an agent can distinguish it from raq_search and raq_call_tool immediately.

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?

Clear context: use this after raq_search to expand a single result, and use native_tool to edit it rather than this reader. Explicit instructions for long records (follow next_offset, or use around with snippet words) make the when-and-how concrete, though it never states what to do if the id is stale or not found.

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