company_ask

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

With no annotations, the description carries the full burden, and it is unusually transparent: it states the tool is read-only, discloses that matching is a fixed word score over a published catalogue rather than a model, explains the no-match fallback, and describes the return shape (documents best-first with verb and answerability). It even says it builds the best ready document, adding behavior beyond any structured field.

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 compact, dense, and front-loaded with the core purpose before technical caveats. It is longer than strictly necessary due to the example questions and matching detail, but each sentence contributes useful information about scope, behavior, or parameters.

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?

The description covers behavior, safety, return semantics, and the key payload field, and an output schema exists so the return shape need not be spelled out. The main gaps are the unexplained wrapper parameters and the absence of explicit routing guidance against sibling tools, leaving the definition good but not fully complete.

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 0%, so the description must compensate, but it only explains one parameter: payload_json takes question, optional limit, and connectors_bound. The required project_id and the other five parameters (now, engine, operation, entity_ref, bundle_json) are left unexplained, leaving significant ambiguity about the invocation payload.

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 and resource: 'Ask a business question in plain words', and gives concrete example questions so an agent can infer what it is for. It clearly describes the deliverable (ranked documents with answerability metadata), but it never explicitly distinguishes itself from sibling ask-style tools like brain_ask or ask_document_agent.

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 examples and 'plain words' phrasing imply when to use the tool, and the no-match fallback behavior gives useful context. However, it names no alternatives and offers no when-not-to-use guidance versus specialised siblings such as company_cash_position or company_explain, so routing is inferred rather than explicit.

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