create_var_model

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

No annotations are provided, so the description carries full behavioral burden. It discloses the asynchronous nature ('Create and start fitting'), the return pattern ('Returns 202-style payload with model_hash; poll get_model_status'), data prerequisites ('at least lags + 10 rows'), strict parameter handling ('unknown keys are rejected'), and naming behavior ('honoured verbatim... falls back to generated API_VAR_*'). This goes well beyond a basic mutation description.

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 long, but the tool has 12 parameters and the length is mostly earned. It is front-loaded with a clear one-sentence purpose followed by structured Args. Minor noise includes issue-tracker references like '(#569)' and '(#575)', which don't aid an agent in calling the tool.

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 complex 12-parameter tool with no output schema and no annotations, the description is remarkably complete: it explains the statistical purpose, the workflow position, every parameter's semantics, constraints, defaults, asynchronous return behavior, and the follow-up status-polling call. An agent has enough information to invoke this tool correctly and know what to do next.

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 fully for the schema. It does: every parameter in the schema is listed in an Args block with its role, constraints, and inter-parameter restrictions (e.g., date_column cannot also be a series, exogenous_vars must not overlap endogenous_vars, base_variable must be endogenous, equity_variables excludes the base). This is exemplary supplementary guidance.

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: 'Create and start fitting a long-term (VAR) model'. It also clarifies how this fits into the broader MMM workflow by mentioning the long-run elasticity bridge and explicitly telling the agent to link it with link_var_model, which differentiates it from the generic create_model sibling.

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 when this tool is appropriate: 'VAR models capture the joint dynamics of several series... produce the long-run elasticity bridge behind the MMM's long_run_rollup results section.' It also gives workflow sequencing ('Fit one, then link it to an MMM with link_var_model'). It doesn't explicitly list exclusions or contrast against generic create_model, but the context is clear enough for selection.

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