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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description's job is to add context, which it does: plan requirements, the agent_not_in_plan refusal, the rule that tests saved before a downgrade are silently excluded, and the exact return keys. It never states outright that the call replaces the entire saved list (the destructive behavior behind the hint), leaving the overwrite semantics to be inferred.

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 scope statement and constraints are front-loaded, and the long model catalog earns its place because model is a free-form string with no enum. It is still a dense single block where the per-agent model lists could be segmented for scanability, but there is little outright waste.

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 two-parameter mutation tool with no output schema, the description covers prerequisites, plan gating, failure reasons, and return keys (enabled_agents, enabled_agent_models). An agent has enough to decide whether it can call this and what it will get back.

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 only 50% — enabled_agent_models has no per-item documentation — and the description fills that gap substantially: which model ids each agent accepts, that two models of the same agent are separate entries, and the agent enum values are implicitly illustrated. The setup parameter is already well documented in the schema, so no duplication is needed there.

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: 'Save the ordered agent/model choices for this project's paid Agent Picks tests.' It then explicitly bounds scope against siblings by saying it 'Does not start a test or change the starter test's fixed models,' which separates it from devtune_start_agent_picks_starter_test and the draft/quote tools.

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 concrete preconditions (existing setup, Agent Picks access, actions.write) and plan-level gating with the exact refusal reason agent_not_in_plan plus downgrade behavior. It does not name the sibling that creates a missing setup (e.g. save_agent_picks_setup) or tell the agent to call get_agent_picks_summary first, so the routing guidance is strong but not fully explicit.

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