check_channels

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

No annotations exist, so the description carries the full burden, and it does substantial work: no transcript fetch, no model invocation, and a cost disclosure ("one polite YouTube request" per channel, capped at max_channels). It does not say what happens if channels.txt is missing or what the returned items look like.

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 short sentences, zero filler, with the core action first and the cost/pagination constraints following. Every sentence adds a fact the agent needs.

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?

Covers purpose, cost, and pagination adequately for a no-output-schema tool, but leaves the days parameter undefined and gives no indication of what fields each listed video carries. For a 2-param tool with no annotations and no output schema, that is adequate but not complete.

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 0%, so the description must define both parameters. It explains max_channels well ("at most max_channels are listed per call") but never mentions days at all — the recency window is left entirely implicit, which is a meaningful gap for a 'new videos' tool.

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 ("List new videos from the channels in your channels.txt") plus the ordering rule ("priority channels first"). The clause "fetches no transcript and calls no model" implicitly separates it from get_transcript and judge_video, so an agent can route correctly without opening schemas.

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?

Gives clear operational context: it only reads channels listed in channels.txt, caps work at max_channels per call, and explicitly says "call again to go on through the rest," which is real pagination guidance. It stops short of naming when to prefer a sibling such as todays_digest instead.

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