mdx_ask

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

Despite no annotations, the description comprehensively explains the internal behavior: introspecting the cube, generating k candidate queries, executing them read-only, and returning a verdict. It also discloses the return structure and the abstain/clarify outcomes, leaving little ambiguity.

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 concise with three sentences: a clear purpose statement, a detailed process overview, and a cautionary note. Every sentence adds value without fluff.

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 the tool's complexity, the description covers input (question, k), process (generation, execution, verification), and output format (status, value, etc.). No output schema is needed because the structure is described. It fully equips the agent to use the tool appropriately.

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?

With 0% schema coverage, the description adds meaning by explaining that 'k' controls the number of candidate MDX queries generated. The 'question' parameter is obvious from context. It doesn't specify the default behavior when k is null, but the schema shows it's null.

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 clearly states the tool's purpose: to answer natural-language questions with verified MDX results. It distinguishes itself by highlighting the self-consistency verdict mechanism, which sets it apart from siblings like mdx_run.

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 context on when to use the tool (for natural-language queries needing verification) and cautions that it never guesses when candidates disagree. However, it does not explicitly state when not to use or mention alternatives like mdx_run for direct MDX execution.

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