List LinkedIn Invitations

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

Annotations already indicate read-only, open-world, idempotent, and non-destructive. The description adds valuable behavioral context about live pages, bounded rescanning, suppression of previously returned identities, and completion reconciliation—details that are not in the annotations and help the agent understand pagination consistency.

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 that front-loads the main action. Although complex, every clause contributes useful information about pagination and deduplication. It is not overly long for the content, but could benefit from splitting into two sentences for readability.

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 the tool's complexity (6 parameters, output schema, annotations), the description explains the core pagination and deduplication behavior well. The output schema fills in return structure, and the description covers the most important runtime semantics. Some parameter purpose is left implicit, but overall it is complete enough for an agent.

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 description adds meaning to the direction and invitation_filter parameters by referencing 'received or sent' and describing the union when filter is 'all'. While cursor and page_size already have schema descriptions, other parameters like context_id and request_id remain unexplained, so the description partially compensates for low schema coverage.

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 clearly states the action ('Read one live cursor page') and resource ('current received or sent invitation inventory'), and it distinguishes itself from sibling tools that send, accept, or ignore invitations. It also adds specific details about the 'deduplicated union' of views, making the purpose unmistakable.

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 clear context for when to use this tool: to read received or sent invitations, and it explains the special behavior when invitation_filter is 'all'. However, it does not explicitly name alternatives or exclusions, though no sibling tool overlaps with listing invitations, so the guidance is adequate.

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