search_heritage

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

Even with annotations declaring readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, the description adds substantial behavioral detail: parallel federated search, partial failure tolerance with error reporting via meta.errors and ctx.warning, separate metadata/digitization licenses, and the explicit statement that only metadata and links are returned—no protected full texts. It also explains client-side filtering and its impact on result counts, which is valuable beyond the annotations.

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-structured: a clear one-liner opening, followed by paragraphs on federated behavior, hit details, client-side filtering, Args, and Returns. It front-loads the purpose and uses headers/bullets effectively. It is somewhat longer than strictly necessary because the Args section partially duplicates schema information, but the additional context earns its place, so it remains appropriately concise.

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 complex federated search tool with multiple parameters and edge cases, the description is complete. It covers error handling, licensing, client-side filtering, pagination, and the output format (ResultEnvelope | str). The presence of an output schema means detailed return values are not needed, but the description still states that results include provenance. This is a thorough and self-sufficient description.

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 description includes an 'Args:' section that covers all parameters and adds meaning beyond the schema. For example, it specifies that date_from/date_to and media_type are applied client-side, that limit/offset paginate per source, and that ctx is injected by the MCP SDK. The schema itself has basic descriptions, but the description enriches them with behavioral context and clarifies the federated semantics.

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 starts with 'Durchsucht Schweizer Gedächtnisinstitutionen (Memobase, Dodis) föderiert,' which clearly states the verb (searches), resource (Swiss memory institutions), and scope (federated across Memobase and Dodis). It is specific, but it does not explicitly differentiate itself from sibling tools like heritage_cross_search or heritage_search_helveticat, so it stops short of a 5.

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 clear context for when the tool is appropriate: it searches specific sources (Memobase and Dodis), and explains the default behavior for collection='all' including failure tolerance. It also notes that date and media type filters are client-side, which guides expectations. However, it does not explicitly mention alternatives or 'when not to use' this tool, so it lacks the exclusionary guidance needed for a 5.

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