sd_search_documents

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

With no annotations, the description carries the full behavioral transparency burden. It goes well beyond a simple action statement by including a CITATION WARNING (never invent IDs/URLs, use exact values), explaining search logic (include_commentary, use_or_logic), mentioning the underlying eXist-db platform, and documenting the return fields (document_id, citation_url, etc.). This provides rich behavioral context for the agent, including a critical safety rule about citations.

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 well-organized with clear headings (PURPOSE, WHEN TO USE, WHEN NOT TO USE, CITATION WARNING, Valid doc_types, Args, Returns), making it easy to scan. It is verbose, though, with some redundancy: the opening one-liner 'Search documents...' repeats the PURPOSE, and the Valid doc_types list repeats the doc_types from Args while adding counts that may not be essential. Still, every section contributes value overall.

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 description covers all 8 parameters, return format, citation handling, and usage context, which is highly complete for a search tool. The main omission is lack of comparison with the sibling mop_search_documents, which represents a contextual ambiguity. Additionally, the 'ctx' parameter is only mentioned as 'FastMCP Context' with no explanation, though its purpose may be obvious from the framework. These minor gaps prevent a perfect score.

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?

The input schema has 0% description coverage, so the parameter explanations in the description are essential. The Args section defines every parameter with meaning and examples: query as space-separated terms, doc_types with allowed values, years as list, date_from/date_to with ISO 8601 format, include_commentary and use_or_logic booleans with defaults, and limit with default. This fully compensates for the schema's lack of descriptions.

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 clearly states 'Search documents in Schleiermacher Digital via eXist-db with facets' and elaborates with a PURPOSE section, naming the tool as the primary search tool for documents by text, type, year, etc. It distinguishes from several siblings in the WHEN NOT TO USE section (filter_letters, search_register, get_document_passages), but it does not differentiate from the sibling tool 'mop_search_documents', which has a nearly identical name and function. Thus it is clear but not fully distinguishing across the sibling set.

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 description provides an explicit WHEN TO USE list (full-text search, filtering by type/year, any document discovery) and a WHEN NOT TO USE list naming three specific alternatives. However, it omits guidance on when to use mop_search_documents instead, which is a direct sibling likely serving a similar role. This leaves a gap in alternative selection, though the provided guidance is otherwise excellent.

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