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

Annotations already cover destructive/idempotent/non-read-only, yet the description adds the pending-only restriction and the two failure modes (stale revision, delivery already started) that force a list refresh. It stops short of stating permissions required or the result of a cancel on an already-cancelled id, but it clearly exceeds the annotation baseline.

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, scope stated first, exclusions and the recovery action after; no filler or repetition of the title.

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 destructive mutation with no output schema and three required parameters, the description supplies the essential guardrails (pending-only, staleness handling). Minor gaps remain around what the response looks like and whether authorization or workspace constraints apply.

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 67% and already documents revision and request_id semantics. The description only indirectly illuminates revision via the 'refresh the list if revision changed' hint and says nothing about the id pattern or request_id retry behavior, so it adds modest value over the schema.

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 ('Cancel one pending ... scheduled message') with an explicit scope limit ('one', 'pending'), and the second sentence separates it from deletion tools that act on already-delivered messages.

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 a clear when-not ('Does not delete a message already sent to Telegram') and an implied prerequisite step ('Refresh the list if revision changed'), but never names an alternative sibling such as telegram_reschedule_message for changing delivery time instead of cancelling.

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