var

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

Goes far beyond the readOnlyHint annotation by disclosing assumptions (stationarity, white-noise residuals, adequate lag order), failure modes (singular covariance, explosive IRFs), and operational guidance (difference/detrend, reduce lags, extend sample). This gives an agent realistic expectations of when the call will fail and why.

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 tightly organized into labeled sections (Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N). Each section carries distinct decision-relevant information with no filler; the most important purpose statement is front-loaded.

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 econometric tool with 11 parameters and an output schema, the description covers assumptions, preconditions, failure modes, minimum sample size, and alternatives. An agent has enough context to decide whether to call it and to interpret common failures without additional round-trips.

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 100%, so the baseline is 3, but the description adds meaningful parameter context: lag adequacy and under-fitting bias for lags, trend='ct' for non-stationarity handling, and ordering/recursive scheme for structural IRF identification. This is useful semantic enrichment beyond the schema.

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?

Opens with 'Estimate a Vector Autoregression (VAR) model' – a specific verb and resource that immediately identifies the tool's function. It distinguishes itself from siblings like arima, bvar, and local_projections through an explicit Alternatives section and by emphasizing VAR-specific assumptions and failure modes.

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?

Names concrete alternatives (sp.local_projections, sp.arima, sp.iv) and provides rich preconditions that clarify when VAR is appropriate. It does not, however, give explicit when-not conditions mapping each alternative to a specific scenario, so it stops just short of full routing guidance.

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