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

Annotations only establish the safety profile (readOnly=false, openWorld=true, non-idempotent). The description goes well beyond that: moderation before airing, hosts paraphrasing rather than reading verbatim, explicit resistance to prompt-injection ('can never make them read text verbatim or follow instructions'), and the concrete generation schedule with timezone.

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?

It is a single dense paragraph, but front-loads the action and outcome and every sentence carries distinct, non-redundant information (schedule, ownership, moderation, injection limits, content guidance, next steps). Nothing reads as filler.

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?

With no output schema, the description correctly sets expectations about what happens after submission and where to retrieve results. Combined with the annotations covering the open-world write profile, an agent has everything needed to invoke this correctly and know what follows.

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 name, station, and question are already fully documented, including the enum and length bounds. The description adds only marginal semantic value by noting the question may come from the agent or the user and that the asker is credited as an AI agent, 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?

The opening sentence gives a specific verb (Submit) and resource (question to the show's AI hosts) plus the outcome (answered on air, credit given). It is immediately distinguishable from siblings like radio_check_question and radio_episode_transcript, which are positioned as follow-up steps.

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 names the alternatives explicitly and the condition that selects them: after the next generation, use radio_check_question for status and radio_episode_transcript for the answer. It also gives content guardrails ('something a curious listener would ask') and clarifies the question can originate from the agent or its user.

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