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

With no annotations, the description carries the full burden and does well: it discloses idempotency ('re-running is safe'), in-place repair of stale rows, the specific fields populated (kind, subject, real preview), and a 10-30 second runtime. It omits auth prerequisites beyond the 'after connecting LinkedIn' hint, rate limits, and failure behavior.

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?

Front-loaded with the core action and the single-pass contrast, then the operational details. Slightly redundant — the 'repair rows that predate those fields' idea is stated twice — plus schema boilerplate in the responses section, but no sentence is truly wasted.

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 zero-param, no-annotation, no-output-schema mutation, the description covers purpose, timing, idempotency, populated fields, and runtime. It could do more on prerequisites (which of the connect_linkedin_* tools must precede it) and on whether it returns a count or summary.

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 tool takes zero parameters, so the baseline is 4; the description correctly implies no input is needed and doesn't waste words on nonexistent arguments.

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 (backfill/pull) and concrete resources (LinkedIn conversations from Unipile into Iridium) with an explicit scope contrast: 'every thread in one pass, not a page at a time,' which distinguishes it from the paginated list_chats/search_chats 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?

Gives clear triggering conditions: run once after connecting LinkedIn, and re-run once after an upgrade to repair older rows. It does not explicit exclude other cases (e.g. 'do not use this to read chats during normal operation'), but the 'once after connecting' framing implies the boundary.

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