weakrobust

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

Annotations declare readOnlyHint=true and openWorldHint=false, so the agent knows this is a read-only analysis tool. The description adds meaningful behavioral context beyond annotations: it is 'Stata-style' (familiar output conventions), 'unified' (combines multiple weak-instrument-robust procedures), and a 'diagnostic panel' (produces a set of diagnostics rather than a single test). The detail parameter further discloses output-depth behavior (minimal/standard/agent) and token sizes, which is substantial behavioral transparency. No contradiction with annotations.

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 a single compact sentence that front-loads the tool's identity ('Stata-style unified weak-instrument-robust diagnostic panel'). It is appropriately sized for a tool whose parameter schema carries most of the detail. It earns its place by conveying the Stata-style and unified-panel nature, though it could have added a second sentence with usage guidance without becoming bloated.

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 (18 params, 4 required, output schema present) and the rich schema descriptions, the description is mostly complete. The output schema exists, so return values need not be described. The main gap is the lack of explicit guidance on when to choose this tool over the many IV-related siblings (anderson_rubin_test, effective_f_test, iv_diag, ivreg). The detail parameter's 'agent' mode and as_handle caching are documented in the schema, so the description does not need to repeat them.

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 baseline is 3. The description itself adds little parameter meaning beyond the schema, but the schema descriptions are already rich (e.g., detail explains token sizes and use cases, h0 explains AR/CLR/K evaluation at beta=h0, data_path lists supported formats and schemes). The description's 'unified' and 'Stata-style' framing adds context for interpreting parameters like vcov and h0, but does not compensate for anything missing since nothing is missing.

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 'Stata-style unified weak-instrument-robust diagnostic panel' names a specific resource (weak-instrument-robust diagnostics) and a specific verb/action (unified diagnostic panel). It distinguishes itself from siblings like anderson_rubin_test, effective_f_test, iv_diag, and ivreg by signaling a unified panel of weak-instrument-robust tests. However, it does not explicitly enumerate which tests are included (AR, CLR, K are only in the schema), so an agent must infer the full scope from parameters.

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 implies usage for weak-instrument-robust diagnostics in an IV setting, and the schema's required parameters (data_path, endog, instruments, y) make the IV context clear. But there is no explicit when-to-use vs alternatives guidance, no mention of when to prefer anderson_rubin_test, effective_f_test, or iv_diag, and no exclusions. The 'unified' wording hints it is a one-stop panel, but the agent is left to infer when this is the right tool among many IV siblings.

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