Search with the native DSL

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

Annotations declare readOnlyHint=true and openWorldHint=true. The description aligns: it describes a read operation ('posts a query ... unchanged') and adds behavioral nuances not covered by annotations, such as: 'RANGE_DAYS n means field >= midnight Europe/Berlin of today + n days, not a window', 'Other fields answer HTTP 500' for ORDER, and operator operand constraints. No contradiction.

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 dense paragraph. It front-loads the core action and then dumps operators and fields. While every sentence adds value, the lack of bullet points or breaks may hinder quick scanning. However, it is not verbose and efficiently packs necessary information. Could be slightly more structured but still effective.

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?

Given 5 parameters (0 required), nested objects, an output schema, and high complexity, the description covers query structure, operator semantics, field lists, FROM variations, ORDER limitations, and provides a reference to a full contract. It addresses pagination implicitly via PAGE parameter, and mentions error behavior for ORDER. No major gaps for a power-user tool.

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 60%, but the description adds substantial meaning beyond the input schema. It enumerates all operators with their operand requirements (e.g., 'Text and temporal operators take exactly one operand; IN and STARTS_WITH OR a list'), lists all field names on lots with examples (e.g., 'estimatedValue (''150000 EUR'')'), and clarifies constraints like RANGE_DAYS behavior. This compensates for schema gaps and aids correct parameter construction.

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 action: 'Posts a WHERE/FROM/PAGE/ORDER query to /bkmk/searches unchanged.' It names the HTTP method (POST), the endpoint, the query structure, and lists operators and fields. This clearly distinguishes it from the sibling 'search_tenders' tool, which likely provides a simpler search interface.

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 extensive operator and field listings, guiding the agent on how to construct queries. It also notes that the 'notices' FROM value has a smaller field set. However, it does not explicitly compare with the sibling 'search_tenders' to state when to use this raw DSL version versus a simpler alternative. Missing explicit when-not or alternatives, but the detail implies usage for complex filtering.

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