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

Goes well beyond the readOnly/destructive annotations by disclosing the billing model (recent_comments_read credits charged per Voyager call the runner makes, not per comment returned), that nothing is written or stored, and that the workspace's own connected account reads free. This is exactly the cost and side-effect context an agent needs before invoking a metered read.

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-loads the core action and cap, then layers in cost and side-effect facts. Four sentences, each carrying distinct information, though the phrasing ('Freshly read...') is slightly informal and the credit paragraphs could be tightened.

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?

An output schema exists, so return shape needn't be described, and the description covers the safety/billing dimensions that matter. It lacks any hint about result volume, pagination, or what happens when the cap is hit, which matters for an idempotentHint=false, open-world read.

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 only 60%; accountId and maxRequests carry no schema descriptions. The description ties maxRequests to the billing/charge model, which adds real meaning, but it doesn't explain the 30-request ceiling, the default of 10, or which account is charged. Baseline 3 for partial coverage with partial compensation.

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 (read) and a precisely scoped resource (recent LinkedIn comments for one lead/profile), plus the maxRequests cap constraint. No sibling tool reads comments, so an agent can unambiguously identify this one against get_leads, get_lead_enrichments, and comment_on_post.

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 clear context for when to reach for it: per-lead comment retrieval, with an explicit pointer to campaignstack_estimate_cost to preview cost before committing. It stops short of stating when-not-to-use or an alternative reader.

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