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

Annotations only declare readOnlyHint=false and destructiveHint=false, and the description adds substantial context beyond that: it is free, runs in the background, takes tens of minutes to an hour, exposes live state in context, and enumerates failure modes. This is exactly the kind of behavioral detail structured fields cannot carry.

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?

The summary/returns structure is front-loaded and purposeful, and the return-shape sentence is compact. The long parenthetical on timing is slightly dense but each clause carries real value, so it is well-sized without being wasteful.

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?

With no output schema, the description compensates by describing the return shape ({started: true, message_backfill} or {started: false, error}) and its failure conditions. Combined with the timing and account-scoping notes, an agent has everything needed to call it 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%, so both `window` (with enum values) and `on_behalf_of` are already documented in the schema, setting the baseline at 3. The description adds no window-format or account-scoping detail beyond what the schema provides.

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 summary states a specific verb (import) and resource (older LinkedIn message history), and anchors it to the UI equivalent 'Import more message history', which removes ambiguity. It doesn't explicitly name the search_linkedin_message_history sibling it differs from, so it falls short of a 5 that would fully route the agent among siblings.

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?

It gives clear context for use (importing older history, right after connecting LinkedIn, the up-to-one-hour indexing wait) and states the two blocking conditions (LinkedIn not connected, import already running). It stops short of explicitly saying when to prefer this over fetching/searching existing messages, so no full when/when-not/alternative breakdown.

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