variety_pick

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

With no annotations, the description carries the full burden. It does disclose meaningful behavior: picks never repeat a recent combination within a scope, and the return includes a plain-text `protocol` to follow. However, it never says whether the pick is persisted server-side (the non-repetition guarantee implies state) or whether the call is side-effect-free, and no permission or rate-limit context is given for a tool that mutates pick history.

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?

Roughly four sentences, front-loaded with the action, then the timing rule, then parameter meaning, then the return value. No filler sentences, though the final return-value sentence partially duplicates information an output schema already provides.

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?

An output schema exists, so return values need not be detailed, and the description still summarizes them. All three parameters are explained despite 0% schema coverage, and the non-repetition semantics plus retry loop give an agent everything needed to call it correctly across a repeated job.

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 0%, so the description must compensate, and it largely does: `kind` is defined as an id from `variety_kinds`, `scope` as a stable account/project label that partitions the non-repetition window, and `avoid` as a list of approach ids to suppress. Only the exact accepted id format is left implicit.

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: "Pick an approach and a form (opening, length, ending) for the next piece of writing." The parenthetical defines the output shape, and the reference to `variety_kinds` ids ties it to the sibling ecosystem. It does not explicitly contrast with `variety_check`, so it stops short of full sibling differentiation.

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?

"Call this before writing each piece of a repeated job" gives an explicit trigger condition, and the retry rule ("If the returned approach does not suit the input, call again with its id in `avoid`") covers the main failure path. There is no guidance on when to prefer `variety_check` instead, which is the one remaining routing gap.

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