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

Beyond the annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false), the description adds valuable behavioral context: it records edges, consumes one LinkedIn search per call, has a daily quota on the free tier, and may return skipped when the lead lacks a member id. This helps an agent anticipate side effects and constraints that annotations alone do not convey.

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 concise and front-loaded: the core action appears in the first sentence, followed by the value proposition, cost constraint, and prerequisite. Each sentence earns its place, though the middle sentence about turning the graph into an actual network is slightly rhetorical. Overall it is well-structured and not padded.

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 should carry return-value and failure semantics, and it partially does by mentioning the 'skipped' outcome. However, it does not describe what a successful response contains, how edges are returned or acknowledged, or what happens on repeated calls. The leadSource parameter is also absent, leaving a meaningful gap in the overall context.

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 schema has 0% description coverage, so the description must compensate. It contextualizes workspaceId ('the workspace's LinkedIn accounts') and leadId ('a lead shares'), but leadSource is never mentioned, and the meaning of 'global' vs 'private' remains unexplained. With three parameters and one entirely unaddressed, the description only partially compensates for the schema's lack of parameter documentation.

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 uses a specific verb ('Scrape') and names the exact resource and outcome: the people a lead shares with one of the workspace's LinkedIn accounts, recorded as person-to-person connection edges. It clearly differentiates this from read-only graph tools by emphasizing that it builds the network graph, making it distinct from siblings like get_lead_connections.

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?

The description gives concrete when-to-use guidance: it consumes a LinkedIn search quota, so it should be called for 'leads that matter rather than in bulk.' It also states an explicit prerequisite: the lead must have a LinkedIn member id, and instructs the agent to enrich first if the call returns skipped. It does not name specific alternative tools, but the usage context is clear.

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