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

Annotations only declare the tool is not read-only and not destructive; the description goes well beyond by disclosing quota ceilings (5 alerted feeds, 5 private feeds), the exact failure mode 'feed_limit_reached', ai_filter-mediated delivery, and the Telegram side effect of notifying the user.

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?

Front-loaded purpose, then parallel 'On:'/'Off:' branches, then the confirmation rule. Dense but every clause carries operational information (limits, failure name, filtering, notification) with no 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?

No output schema exists, and the description compensates by naming the error condition the caller may receive; quota, filtering behavior, confirmation requirement, and side effects are all covered for a 3-parameter mutation.

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% and already documents all three parameters, so a 3 baseline applies; the description adds genuine value by explaining the downstream consequence of each `on` value and the conversational precondition behind `user_confirmed`.

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 ('Turn Telegram notifications for a feed on/off') and immediately clarifies what each state means, including that turning alerts off leaves the feed intact — which separates it from delete_feed and set_feed_paused without naming them.

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 explicit conditions for each parameter value (on: true sends every new matching job; on: false keeps the feed private), states the prerequisite slot limits, and adds a hard procedural rule ('Ask the user first, then pass user_confirmed: true').

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