Keyword Search in Document

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

The description adds no behavioral context beyond the annotations: no return format, matching semantics, pagination, or scope details. The annotations (readOnlyHint, idempotentHint, non-destructive) cover safety, but the description itself is silent on what the agent should expect from the 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?

One short sentence with no filler and the keyword scope is front-loaded. It is efficient, although it is so terse that it leaves out contextual value that longer guidance could provide.

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 search tool with no output schema, the description should explain what the response represents and how this relates to the surrounding KWS workflow; it does neither. With dozens of search/kws siblings, the missing distinction and return-value context makes this incomplete for reliable tool selection.

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?

Input schema covers all three parameters with descriptions (Collection ID, Document ID, Search query string), so the baseline is 3. The description adds no extra meaning about query syntax, the collId/id relationship, or how the query is interpreted.

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 states a specific action ('Search') and a scoped resource ('keywords within a document'), so an agent can tell it is a document-level keyword search. However, it does not explicitly distinguish this from the many kws/search siblings such as transkribus_kws_get_hits or transkribus_search_keyword.

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 phrasing implies usage when the agent needs to find keywords inside a specific document. It gives no explicit 'use X instead' guidance or exclusions, which matters in a large sibling set with several search/kws tools.

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