search_data_room

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

With no annotations, the description carries the full burden, and it does disclose meaningful behavior: the exhaustive-vs-ranked switch on `query`, the top_k cap, and that each result carries citable articles. It omits read-only status, auth requirements, and pagination behavior, but the mode-dependent output semantics are well surfaced.

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?

Four tight sentences with the key behavioral distinction front-loaded, no repetition of the schema, and no filler. Every sentence adds a distinct fact.

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 search tool with no annotations and no output schema, the description covers the essential invocation semantics (mode switching, top_k, citable articles). It stops short of describing result shape, pagination, or limits, which for an exhaustive-mode tool is a minor but real gap.

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 67%, below the 80% baseline, so the description should compensate. It clarifies that top_k only applies when `query` is supplied, which is useful, but the schema already documents that dependency, and the nested filter fields receive no additional explanation from the description.

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?

States a specific verb and resource ("Recherche dans la data room") plus the two operating modes, so the agent immediately knows this is a filtered/full-text search over contracts. It does not, however, differentiate itself from the sibling get_contract, which also retrieves contracts.

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 explains the two modes (no `query` = exhaustive list of everything passing filters; with `query` = ranked top_k), which implies how to invoke it for a given intent. But it never says when to prefer this over get_contract or when the exhaustive mode is appropriate versus the ranked one.

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