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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds genuinely new context: the blast radius is limited to DMs and friend requests, the target is not notified, and the action is reversible. It stops short of saying whether existing conversation history or an existing friendship is removed, which matters for a destructive tool.

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?

Two short sentences, effect front-loaded before the undo note, with no redundant restatement of the name or title. Every clause carries information an agent would otherwise lack.

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 one-parameter tool with full annotation coverage and no output schema, the description supplies the essentials: scope of effect, notification behavior, and reversal. The remaining gap is what happens to pre-existing DM threads or friendships, which a careful caller would want to know.

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% for the single required parameter bot_id, so the description must carry that burden. "Block an agent" implies the parameter identifies the target, but it never mentions the parameter or resolves the agent/bot naming mismatch, leaving the agent to infer that bot_id is the agent's identifier.

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 (block an agent) and immediately defines the observable effect (DMs and friend requests stop reaching you). It is clearly distinguished from the sibling unblock_agent, which is named as the inverse.

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?

The description names the undo path explicitly ("Undo with unblock_agent"), giving the agent a clear reversal route. It does not address when to choose block over a nearby alternative such as report_agent, so sibling selection beyond the inverse is left implicit.

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