de_dip_search

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

Annotations already carry the safety profile (readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true), so the bar for additional value is lower. The description adds genuinely useful context beyond the annotations by disclosing API key handling: 'Uses the documented public API key by default (rotates ~yearly; override with DE_DIP_API_KEY)'. No contradiction with annotations exists. It falls short of explaining error behavior or rate limits, so a 3 is appropriate.

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 primary purpose is front-loaded and the text is compact overall. The sentence 'Legislative history... is a standard aid of German statutory interpretation' provides useful domain motivation for a legal researcher but is somewhat tangential to actually invoking the tool, keeping this from a 5.

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?

An output schema exists, so return values need no prose explanation; the input schema fully documents all parameters; and annotations cover the safety profile. The description supplies the domain scope and the API-key behavior that structured fields don't convey. The one notable gap is sibling routing (how this differs from de_search or de_dip_get_document), which is minor given the rich schema and output schema.

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% — every sub-property (titel, cursor, date_end, resource, zuordnung, wahlperiode, vorgangstyp, dokumentnummer) has a description, and the nested query object itself carries a summary. Per the rubric, high coverage earns a baseline 3. The tool description adds only marginal parameter context, mapping the covered document types to the resource enum, so it doesn't need to compensate.

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 opens with a specific verb-resource pair ('Search the Bundestag DIP - Germany's official parliamentary documentation') and enumerates the exact content types covered (Drucksachen, plenary transcripts, legislative procedures of Bundestag and Bundesrat). This is clear and specific. However, it does not differentiate from siblings like de_search or the several case-search tools (de_rii_case_search, de_oldp_case_search), so an agent must infer the distinction from the domain terms alone rather than an explicit boundary.

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 explicit when-to-use vs alternatives guidance is given. The description implies this is the entry point for DIP parliamentary documentation, and the note that 'Legislative history... is a standard aid of German statutory interpretation' gestures at a use case, but there is no statement of when to prefer this over de_search, de_dip_get_document, or the case-law searchers. The agent must route by inference.

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