telegram_classify_channels

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

Adds value beyond annotations by disclosing unbounded scope (all channels auto-included) and slowness, consistent with openWorldHint=true. However, readOnlyHint=false hints at possible side effects, and the description never clarifies what, if anything, gets written or modified — a meaningful gap for a diagnostic tool that should be safe to run.

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?

Core purpose is front-loaded, followed by diagnostic context, usage caveat, then Args. Slightly redundant — the diagnostic purpose is restated in two adjacent sentences — but overall efficient and well-ordered with no wasted 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?

Given the output schema covers return values, the description handles purpose, scope, performance, and all three parameters adequately. Remaining gaps are the unclarified read/write behavior and lack of explicit sibling routing, but nothing an agent needs to call it correctly is missing.

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?

With 0% schema description coverage, the description carries full parameter documentation: sample (count per channel, default 80), threshold (0~1 density, default 0.05), min_mentions (cumulative count, default 3). It adds meaning well beyond the bare integer/number types and includes defaults and a range.

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+resource+outcome: scans all joined channels and measures/reports 'stock mention density' per channel. The diagnostic purpose (distinguishing stock-focused vs macro/small-talk channels) clearly separates it from the many telegram_* siblings without opening any schema.

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?

Provides clear context on when to use it — as a diagnostic tool for channel composition — and a performance caveat ('scans all channels so it's slow, use only when needed'). However, it doesn't name alternative tools or explicitly state when NOT to use it, leaving some sibling differentiation to inference.

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