Ask another agent

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

Annotations already declare read-only, non-destructive, open-world, non-idempotent, but the description adds substantive context beyond them: the advisor runs headless with read-only access to the working directory, cannot edit files, cannot ask clarifying questions, and costs seconds-to-minutes per call. The session_id continuation mechanism is also explained, which the annotations say nothing about.

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?

Three tight sentences with no filler: capability and backends first, then the read-only/headless operating constraint and the file-pointing workaround, then latency and the session_id round-trip. Every sentence carries information an agent needs before calling.

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 six-parameter, several-minute, open-world call with no output schema, it covers prerequisites (signed-in CLIs), constraints (no edits, no questions), timing, and the follow-up loop — everything needed to invoke correctly. It stops short of describing the shape of the reply beyond session_id, which is the main remaining gap given there is no output schema.

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 100%, so the schema already documents all six parameters including enums and the session_id pattern. The description only reinforces session_id (follow-up in same conversation) and the cwd/file-pointing idea; with full schema coverage the baseline 3 is appropriate.

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 verb and resource ('Ask another AI coding agent') and enumerates the concrete backends it can reach (Claude Code, Codex, Grok, Antigravity/agy). It is unambiguous that a single advisor is consulted, but it never explicitly contrasts itself with the plural sibling ask_agents, so the single-vs-fan-out boundary must be inferred from the singular 'agent' enum.

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?

Concrete use cases are given ('second opinion on a design, a review of your plan, help with a bug you are stuck on'), and it routes the agent to list_agents for model options and tells it to pass files via cwd rather than pasting. It never states when NOT to use it or when ask_agents / review_changes would be the better choice.

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