pick_agents

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

No annotations are provided, so the description carries full burden. It discloses the round-robin algorithm using preference_order and last_used_at, and mentions healthiness and cross-provider diversity. It does not mention side effects, rate limits, or authorization, but the selection behavior is well-described.

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 main description is concise and front-loaded. The ROUTING NOTE adds length but provides essential usage guidance. The structure separates core functionality from usage notes, but could be slightly more succinct.

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?

The tool has 3 parameters with nested objects and no output schema. The description explains selection logic and usage contexts, but does not specify the return value format (e.g., list of agent IDs or objects). This gap makes it incomplete for an agent to understand what to expect.

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 0%, so the description must compensate. It briefly describes each parameter: n count, filter with default tier, and min_distinct_providers for diversity. However, it does not explain sub-properties of filter (tags, exclude_ids) in detail, leaving some ambiguity.

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 clearly states the tool picks up to N distinct healthy candidates using round-robin with preference_order and last_used_at. It also mentions optional min_distinct_providers for cross-provider diversity. This distinguishes it from sibling tools like list_agents (which lists without selection logic) and get_stats (which provides metrics).

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 ROUTING NOTE provides explicit guidance on when to use the default weak tier versus the strong tier. It explains that weak tier is intentional for most routine tasks and strong tier should only be used for deep reasoning tasks. This directly helps the agent decide when to invoke this tool with different filter settings.

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