linkedin_prepare_action

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

Annotations state readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the agent knows it's a non-read-only, non-destructive, closed-world operation. The description adds crucial behavioral context: it's a preparation step that returns a preview, proposal_id, and digest, and does not perform the action. However, it doesn't detail what happens if the preview is not shown or the consequences of skipping execution.

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 description is a single, dense sentence followed by a critical instruction. It is front-loaded with the core purpose and then lists parameter specifics. However, the parameter enumeration is somewhat lengthy and could be slightly more structured for readability, but it remains efficient with no wasted words.

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?

Given 8 parameters, no output schema, and 0% schema description coverage, the description provides essential completeness: it defines the kinds and associated parameters, and clarifies the non-execution behavior and required workflow. The only gap is that it doesn't specify the exact format of the returned preview or the digest, but that is arguably beyond the scope of a preparation tool.

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 0%, meaning the description must compensate. It extensively documents the parameters for each kind: for 'post', it lists text, optional visibility (PUBLIC|CONNECTIONS), optional link_url/link_title/link_description; for 'comment', post_url and text; for 'react', post_url and optional reaction; for 'delete_post', post_url. This adds significant meaning beyond the enum and string types in the schema, though it doesn't specify max lengths or default values already present in the schema.

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 description explicitly states a specific verb ('Prepare (not perform)') and resource ('one LinkedIn action'), and clarifies the output is a preview, proposal_id, and digest. It clearly distinguishes itself from the sibling linkedin_execute_action by emphasizing non-execution and the need to preview first.

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 explicit when-to-use context: 'Always show the user the exact preview before calling linkedin_execute_action.' This directly names the alternative tool and the condition that selects it, leaving no ambiguity about the workflow.

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