did_multiplegt

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

Annotations only declare readOnlyHint=true and openWorldHint=false; the description adds substantial behavioral context: assumptions (parallel trends, stable effects, no anticipation), preconditions on data structure, failure modes when nobody switches treatment, and the limitation that switching both on and off is handled. It also flags roadmap items and validation evidence, exceeding what annotations alone provide.

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 organized with labeled sections (assumptions, pre-conditions, failure modes, validation). All information is relevant, though the truncation at 'Joint placeb...' and the roadmap detour add slight noise. It is front-loaded with the estimator definition and remains scannable.

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 estimator with 18 parameters, an output schema, and read-only hints, the description covers the estimator's mechanics, scope, assumptions, prerequisites, failure modes, and alternatives. The output schema covers return values, and the schema covers parameter details, so the description completes the contextual picture without redundant repetition.

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. The description adds value by clarifying the treatment variable must be binary and time-varying, requiring a long-format panel with at least two periods per unit, and by explaining that placebo/dynamic/boostrap features are supported. This goes beyond the schema's bare parameter descriptions without duplicating them.

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 names a specific estimator (DID_M), gives the intuition as a weighted average of consecutive-period DID cells comparing switchers to stayers, and explicitly differentiates it from Callaway-Sant'Anna. An agent can immediately identify what this tool computes and how it differs from closely related siblings.

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?

It states when the estimator is appropriate: treatments that switch on and off, and explicitly says to fall back to callaway_santanna for staggered-adoption designs. Pre-conditions (long panel, binary treatment, ≥2 periods) and failure modes (no switching cells) give clear guidance on when this tool should and should not be used.

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