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

With no annotations, the description carries the full load and does well: it discloses the 5-credit cost, the irreversible external effect ('REAL'), the side effect that the AI stops messaging and a human takes over, and the CRM stage transition to Manager Dialog. It omits failure modes, rate limits, and what happens if the contact is already under takeover, which keeps it from a 5.

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 action and the 'REAL' flag, and every clause (cost, takeover, CRM move, approval gate) carries information. The dense semicolon-chained sentence packs four distinct facts together, which is slightly harder to scan than separate clauses.

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 2-parameter irreversible outbound-send tool with no annotations and no output schema, the description covers costs and side effects but leaves the agent without parameter sourcing guidance or any statement of what a successful/failed send returns. Adequate, but the chat_id provenance gap is a real omission for a tool with no schema help.

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 description coverage is 0%, so the description must explain both parameters and does not. 'In the chat' hints that chat_id refers to an existing LinkedIn conversation, but there is no guidance on where chat_id comes from (e.g. list_linkedin_conversations / get_linkedin_conversation) and no constraint on 'text' length, formatting, or media support.

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 ('Send a REAL LinkedIn message in the chat') and immediately distinguishes itself from the preview sibling and from campaign/telegram send tools by naming the actual external effect. An agent can tell what it does and what it is not without opening the schema.

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 a hard precondition: 'Only after the user approved preview_send_linkedin_message', which names the required alternative tool and the approval gate. It does not cover adjacent cases (e.g. when to prefer takeover_linkedin_contact or campaign-thread replies), so it is clear context rather than exhaustive when/when-not guidance.

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