Find Documents

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds only 'across collections' and 'using filters' as behavioral context. It does not disclose pagination defaults, result count limits, or how filters combine (AND vs OR, partial vs exact match), though nValues, index, exactMatch, and caseSensitive parameters suggest these behaviors matter. With strong annotations, a 3 is appropriate — the description adds minimal context beyond them but does not contradict them.

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?

The description is a single clear sentence with no fluff or repetition of the title. It is front-loaded with the core action. It could arguably add more operational detail, but as written it is efficiently structured with zero wasted words, which is slightly above the minimum viable bar.

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 tool with 29 optional parameters and no output schema, the description is far too thin. It does not explain what the returned documents look like, how pagination behaves, whether results span all accessible collections or require a collId, or how this differs from transkribus_coll_find_documents_post/old and transkribus_coll_count_find_documents. The annotations cover safety but not operational completeness, and the schema's terse 'Filter by X' descriptions leave search semantics unclear.

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 the schema carries the documentation burden for all 29 parameters and the baseline is 3. The schema's parameter descriptions are terse ('Filter by ID', 'Filter by description') but some do add semantics ('Number of results (-1 for all)', 'Start index (0-based)', 'Sort direction: asc or desc'). The tool description itself adds no parameter-level meaning beyond what the schema provides, so it does not push above baseline.

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 verb ('Search') and resource ('documents across collections') and notes that filtering is supported. This is clearly a query/read tool. However, it does not differentiate from the closely named siblings transkribus_coll_find_documents_post, transkribus_coll_find_documents_old, and transkribus_coll_count_find_documents, so an agent cannot tell which variant to pick from the description alone.

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?

No guidance is given on when to use this tool versus alternatives such as transkribus_coll_find_documents_post, transkribus_coll_find_documents_old, or transkribus_coll_count_find_documents. There is also no mention of prerequisites (e.g., whether collId is expected, authentication requirements, or when the count variant would be more appropriate). The description leaves all selection logic to the agent.

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