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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the description's value-add is the behavior it does disclose: blocking works via handle even before the user has messaged, and via conversation_id the block applies cross-channel. It does not state whether the block is reversible via unblock_user, whether an unknown handle errors or creates a stub, or what is returned.

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 sentences, front-loaded with the action and then the input rule, with no filler or redundancy.

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 two-parameter mutation with no output schema, the description covers the action, both inputs, and the exactly-one constraint. It leaves gaps only on edge behavior (neither/both supplied, unknown handle, reversibility) that are minor for this tool's complexity.

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 only 50% because conversation_id is undocumented, and the description compensates by defining it as the person behind an existing conversation on any Meta channel. It also adds the mutual-exclusivity constraint (exactly one of the two), which appears nowhere in the schema (no required fields, no oneOf).

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 a user") and enumerates the two identification modes, so the agent knows exactly what the tool does and which inputs select which mode. The operation is clearly distinct from siblings like unblock_user and list_blocked_users 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?

"Send exactly one of ig_username ... or conversation_id" gives explicit routing guidance between the two input paths, which is more than an implied usage. It stops short of naming alternatives (e.g., list_blocked_users to check state, or unblock_user) or stating when blocking is the right action versus muting/handling.

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