ingest_data

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the read-only nature is covered. The description adds meaningful behavioral context beyond annotations: it explains join-key auto-detection, merging behavior, polarity mapping, and the conditional simulation_result return. This gives the agent a clear picture of how the tool processes data.

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 moderately long but every sentence contributes: purpose, detection behavior, run_simulation flag, multi-table behavior, and return fields. It is well-structured with the core purpose front-loaded. Minor redundancy exists with the run_simulation explanation, which mirrors the schema, but overall it is efficient.

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?

With no output schema, the description compensates by listing return fields (fields_detected, records_analyzed, join_applied, engine, objective_function, variables, simulation_payload, simulation_result). It explains the primary branching behavior (run_simulation=true) and multi-table handling. Missing details like error cases or unsupported formats are minor for this tool's complexity.

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%, so the schema already documents all four parameters. The description does not add new parameter-specific meaning beyond restating run_simulation's behavior and the multi-table merge behavior. A baseline 3 is appropriate because the description provides no additional semantic value for parameters.

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: 'Auto-map tabular data to a simulation payload.' It goes beyond the tool name by detailing what auto-mapping entails—detecting distributions, polarity, units, and building the objective function. This distinguishes it clearly from sibling data tools like onboard_dataset, connect_data, and simulate.

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 clear usage context: run_simulation=true executes immediately and returns results, and multiple tables are joined automatically before analysis. It does not explicitly name alternative tools or exclusion criteria, but the intended workflow is evident from the description.

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