search_text

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

No annotations are provided, so the description carries the full burden; it does disclose the key behavioral constraint (indexing scope covers only four content types, handwriting excluded) and that results point back to notebooks. It says nothing about permissions, result ordering, or pagination behavior, which matters given the limit parameter.

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 with no filler; the scope statement comes first and the exclusion/remediation second. Every sentence earns its place.

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?

The output schema covers return values, so the description needn't explain them, and the indexing-scope limitation is well covered. But for a parameterized search tool with zero schema documentation, the description leaves query syntax and the limit parameter entirely unspecified.

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 0%, so the description should compensate. It mentions no parameter at all — neither the required 'text' query nor the 'limit' cap (default 50) — leaving the agent to infer semantics such as whether text is a phrase, substring, or boolean query.

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 (search) and resource (the live library's indexed text), and enumerates exactly which content types are indexed: pdf text, typed text boxes, outlines, bookmarks. This distinguishes it from content-reading siblings like render_page or page_ink without needing to open any schema.

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?

Explicitly excludes handwriting content and redirects to render_page on the hit notebooks, which is a clear when-not-to-use plus alternative. It does not, however, say when to prefer text search over other navigation siblings (library_tree, notebook_info), so routing is only partially covered.

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