ddb_search

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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantive behavior beyond them: the DDB indexes descriptions rather than page text, coverage depends on what archives deliver, absence of hits is not evidence of absence, and date filtering is overlap-based. It also specifies the citation obligation (archive plus signature) and what fields each hit carries, which is exactly the kind of context the annotations cannot supply.

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 opening line is front-loaded with the verb and resource, and subsequent sentences each carry a distinct, non-redundant caveat (hit identity, coverage limits, date semantics, permalink chaining). It is dense but earns its length; the mid-sentence line wrapping slightly hurts scannability without wasting words.

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 an 8-parameter, zero-required search tool with no output schema and thin annotations, the description supplies what is missing: the shape of a hit (institution, signature, dates, context), pagination is covered by the schema, and the result-interpretation caveats are stated. An agent can call it and read its results correctly without additional context.

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 coverage is 100%, so parameter documentation alone is adequate and the baseline is 3. The description still adds meaning: 'Dates match by overlap' resolves how year_from and year_to combine beyond the schema's per-parameter wording, and 'Empty lists everything the filters keep' explains the empty-query default. The archive parameter's matching rule and permalink semantics are covered in-schema, so no further lift was needed.

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?

Opens with a specific verb and resource ('Search the Deutsche Digitale Bibliothek') and immediately narrows scope to 'archives' finding aids and digitised objects.' It also clarifies what the results are ('A hit is a finding aid, not the record'), which prevents an agent from mistaking hits for primary records. It stops short of naming when to prefer it over regional search siblings such as hessen_search or nrw_search, so the differentiation is by resource scope rather than explicit routing.

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?

Gives explicit interpretive guidance an agent would otherwise get wrong: 'no hits is not a negative' and 'Dates match by overlap,' plus the chaining rule 'labw_permalink means labw_image can read its pages.' The sector parameter is steered toward Archivportal-D coverage. It lacks explicit when-not-to-use or a named alternative for regional queries, so it stops short of full routing guidance.

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