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

Beyond the annotations' read-only, idempotent, and non-destructive profile, it discloses that calls count as browsing and provides concrete quotas of 30 per hour and 100 per day. The recommended randomized checking cadence adds further operational context that directly affects safe invocation.

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?

Four short sentences front-load platform eligibility and result scope, then cover quotas and polling frequency. Every statement supplies actionable information without repetition or unnecessary background.

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 simple read-only list operation, the definition covers scope, one returned field, platform restrictions, rate limits, and recommended usage. Its main omissions are pagination and parameter behavior, which matter more because there is no output schema and the input schema has no descriptions.

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 0% schema description coverage, the description needed to compensate but leaves limit and cursor entirely unexplained. "This account" and "LinkedIn accounts only" provide some context for account_id, but there is no guidance on pagination, cursor usage, or limit behavior.

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 precisely scopes the listing to pending invitations that "this account sent" and includes their sent times. "LinkedIn accounts only" adds a platform restriction, while the sent-only scope distinguishes it from list_received_invitations.

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 applicability and polling guidance: use it only for LinkedIn accounts and check "a few times a day, at random, not every hour." This supplies both when to use the tool and when not to repeat it, though it does not explicitly route received-invitation requests to the sibling tool.

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