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

With no annotations, the description carries the full burden and does disclose the critical non-obvious side effect: a NEW upstream account id is created, so past outreach stays on the old id, history can appear empty, and campaigns may need re-pointing. It stops short of the returned value, token handling, idempotency, or error behavior, so it is strong but not complete.

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, front-loaded with what the tool does, then the consequence, then the approval gate. Nothing is filler.

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 no-annotation mutation with no output schema, it covers the main risk (identity change and its downstream effects) and the approval prerequisite. It omits what the call returns, especially whether the new account id comes back to the caller, which matters given the described id churn.

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?

The schema has 0% description coverage and the description never explains what `id` refers to (old account id? workspace id?). 'Per-account history stays attached to the old id' hints the id is an account identifier but does not resolve whether this is the id being replaced or a new one.

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 ('re-authenticate a LinkedIn account whose session died') and the triggering condition, which clearly separates it from connect_linkedin_account (new connection) and disconnect_linkedin_account.

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 states the precondition: only call after the user reviewed `preview_reconnect_linkedin_account` and approved. That names the alternative tool and the condition selecting this one.

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