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

Goes well beyond the destructiveHint/idempotentHint annotations by disclosing the two consequences an agent most needs to know: nothing is sent, and the other person is not notified. It also explains that the block is symmetric — the user cannot write to them either — which is non-obvious and materially affects whether the agent should call it.

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 sentences, each doing distinct work: scope, side-effects, then the invocation precondition. The most decision-critical constraint (user-initiated only) is placed last where it reads as a guard rather than getting buried.

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 mutation tool with no output schema, the description supplies the full behavioral picture: what it affects, what is not disclosed to the counterparty, symmetry of the block, and how to reverse it. An agent has everything needed to call it safely and correctly.

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 the single parameter's description already spells out accepted, waiting, and already-asked contacts. The tool description reinforces the multi-state acceptance ('accepted, waiting or already asked' is echoed via the three blocking cases), so no meaning is lost, though it adds little beyond the schema. Baseline 3 plus the reinforcement of valid inputs warrants a modest bump.

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?

Uses a specific verb-and-resource framing ('Stop somebody reaching the user') and then enumerates the three distinct states it collapses — refusing a waiting request, ending an accepted contact, and pre-emptive blocking. This makes it clearly distinguishable from siblings like accept_contact, withdraw_invite, and unblock_contact without needing to open their schemas.

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?

Explicitly routes the agent: 'Call it only when the user asks for it in their own message' is a hard usage constraint, and 'unblock_contact lifts it' names the inverse tool. Both the when and the when-not (no inferring intent on the user's behalf) are stated.

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