sa_analyze

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

With no annotations, the description carries the full burden and does so richly: it discloses determinism via r_seed, dependency failures (Rscript/LSDsensitivity), a sub-0.5 fit warning, polynomial failure on negative-mean responses, kriging numerical failure on coincident points, and edge behavior for '_'-prefixed variables and multiple instances.

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?

Front-loaded with the core verb and the two metamodel branches before constraints, which is the right ordering. The prose is dense and run-on in places, but nearly every clause carries a behavioral fact an agent needs, so the length is largely earned for a 9-parameter 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 tool with no output schema and no annotations, the description supplies the return shapes (Q2/R2, effects/interactions table, mu/mu_star/sigma/se/p_value), the scaling and sorting of ee output, and the operational preconditions. Nothing essential to invoking or interpreting it is missing.

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?

At 0% schema coverage the description must compensate, and it explains metamodel, ini_drop, n_keep, r_seed, levels and jump with real meaning, including the MAX_STEP constraint and -1 sentinel. It leaves model, config and variable essentially defined only by surrounding prose, so one or two parameters remain under-specified.

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?

States a specific verb and resource: 'Analyse the design results for one saved variable with LSD's R package LSDsensitivity.' It clearly delineates this as the analysis step, distinct from the design/run siblings (sa_create_design, sa_run_design), so an agent can place it without opening any schema.

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?

Gives strong conditional guidance: kriging/polynomial for lhs/random/nolh, 'ee' chosen automatically for an ee design, and that mixing metamodels with the wrong design is an error. It also routes around failures ('use kriging then', 'try polynomial'). It stops short of explicitly naming sibling tools or stating the prerequisite ordering relative to sa_run_design.

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