wait_for_agents

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

With no annotations, the description carries the full burden and does disclose real behavior: the call blocks, is capped at roughly 55 seconds, returns per-agent status plus latest output, and signals incompleteness via a done flag. It does not explain what happens if the cap is hit without completion (error vs. done=false), and the '~55s' cap is not reconciled with the timeout_seconds default of 50.

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?

Two dense sentences with the blocking constraint and the retry condition front-loaded; nothing is padding. The parenthetical '(max ~55s)' and the trailing 'mode' note make it slightly harder to scan than it needs to be.

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 three-parameter blocking tool with no annotations and no output schema, the description covers the return shape and the re-call rule, which is the core. It leaves out mode semantics and timeout-vs-cap behavior, which an agent needs to invoke it correctly in edge cases.

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 at least names the legal mode values ('all' or 'any') that the schema leaves untyped, but never explains what each mode means, and it says nothing about the agent_ids format or how timeout_seconds interacts with the ~55s ceiling.

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 states a specific blocking verb and resource: wait until the given agents finish their current work. It is clearly distinct from read-only siblings like fleet_status or get_agent, but it never names those siblings or contrasts blocking wait vs. status polling, so differentiation is left implicit.

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 gives one useful operational rule — 'call again if done is false' — which defines the polling loop. However, it never says when to prefer this over fleet_status/get_agent, nor when not to use it (e.g., non-blocking contexts), so usage is only implied.

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