Ignore Prepared LinkedIn Connection Request

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

Adds substantial behavioral context beyond annotations: discloses it changes the account, requires approval confirmation, verifies preview/payload hash/expiry/idempotency/profile identity/request controls, and performs a fresh read to confirm controls absent. No contradiction with destructiveHint/idempotentHint.

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?

Single dense paragraph leads with the critical 'Account-changing action' warning, then approval conditions, then the exact behavior and post-verification. Every sentence adds necessary safety or operational detail with no fluff.

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 execute tool with output schema available, the description covers authorization, operational steps, verification checks, and post-action confirmation. It is complete enough for an agent to select and invoke it properly.

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 33% (descriptions for action_id and payload_hash). The description refers to the preview, payload hash, and idempotency checks, giving some meaning, but does not explain context_id, request_id, approval_preview structure, or idempotency_key semantics. Partial compensation for low coverage.

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?

The description clearly identifies the action ('Ignore exactly one immutable incoming-request draft'), names the resource (prepared LinkedIn connection request), and distinguishes it from sibling execute tools like accept/send by specifying the ignore operation. The phrase 'after the server verifies' ties it to the prepare step.

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?

States an explicit precondition: invoke only when the configured approval policy authorizes this exact execute tool, with interactive confirmation as the safe default. It implies this is the execution step after prepare (references preview/payload hash) but doesn't name alternatives or exclusion conditions, so not a full 5.

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