ask_marvin

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

With no annotations, the description carries the full burden, and it does disclose the single most surprising behavior: the call may return a response_id instead of an answer, meaning results can be deferred. It does not explain what triggers the async path, expected latency, or that a paused request may need cancelling, which leaves meaningful gaps for an un-annotated tool.

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?

A single clause with zero filler, front-loading the action and then the two possible outcomes. Nothing could be removed without losing information.

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 tool with a full output schema and documented parameters, the description covers what it does and the one non-obvious outcome. The only missing piece, naming the polling sibling, belongs to usage guidance rather than making the definition incomplete.

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 100%; conversation_id already documents how to continue a thread. The description adds no syntax, format, or constraint detail beyond the schema, so the baseline 3 applies.

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 ("Ask Marvin a question") and adds the distinctive dual return mode. It does not name or distinguish itself from siblings like get_response or list_conversations, so the agent must infer the relationship, but the core purpose is unambiguous.

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 phrase "or a response_id to poll" implies a follow-up step exists but never names get_response as the tool to poll with, nor mentions cancel_response. Usage is implied rather than instructed, leaving the agent to guess the async workflow from sibling names alone.

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