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

Annotations already declare readOnlyHint/openWorldHint=false, but the description adds real provenance: data comes from the extension's sync of LinkedIn's connection list (on Connections tab load and daily while Inbox is on), with synced_through indicating freshness. It also discloses pagination via next_cursor and the safety note that drafts are not auto-sent. Caching/staleness windows are implied rather than stated, keeping it at 4.

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?

Purpose is front-loaded, then provenance, then filters, then drafting handoff – a sensible progression with no filler sentences. It is dense single-paragraph prose, which slightly hurts scannability for six parameters.

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 read-only list tool with no output schema, it supplies what an agent needs: what records appear, how fresh they are (synced_through), how to page, and how filters compose. The undocumented limit parameter and unstated result-shape beyond next_cursor are the only gaps.

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?

With only 50% schema coverage, the description compensates well: it defines messaged values ('no' = never messaged, 'yes' = has a conversation, 'any'), query matching rules (case-insensitive, all words must match, literal text, no job-title interpretation), days default/max, and cursor = next_cursor. Only limit is left entirely undocumented.

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?

Opens with a specific resource and scope: 'People the user is connected with on LinkedIn, newest connection first, including people they have never messaged.' This clearly separates it from conversation-listing siblings such as list_conversations and recent_messages.

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 concrete filter-selection advice, including the non-obvious steer to use a broad query plus headline data rather than literal job-title words, and routes drafting to draft_reply. It does not explicitly state when to prefer get_contact or list_conversations instead, so it stops short of full when/when-not coverage.

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