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

Goes well beyond the annotations: it discloses that the call consumes Leadbase credits, that completed usage cannot be undone, that it starts async background research and returns batchId/sheetId immediately, that only verified matches count and results are never padded, and that interrupted responses can be recovered by reusing idempotencyKey. That covers cost, irreversibility, and async semantics, though it doesn't quantify rate limits or credit-per-row costs.

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-loaded with purpose, then alternatives, then cost/behavior, then recovery. Dense but every sentence carries operational weight; slightly long, but the length is justified by a paid async operation with several failure modes.

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 values need not be spelled out, yet the description still signals batchId/sheetId and the follow-up tools. Combined with rich annotations and cost/idempotency disclosure, an agent has everything needed to invoke it safely and correctly.

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 50%, but the description compensates: it clarifies that count is a target, not a credit budget, that identityField must be a text/URL field used for dedupe, that fields are typed, and that sourceUrl is reserved and auto-added. Only 'title' is left implicit, so it meaningfully exceeds the schema text.

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 and resource ('Create a new private sheet and research a list of companies, people, products or public web content into new rows') and explicitly separates itself from siblings sheets.enrich (existing rows) and enrichment.start (no sheet). An agent can route correctly without opening another schema.

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?

Names the alternatives and the exact conditions that select them: use sheets.enrich for filling cells in existing rows, enrichment.start for findings without a sheet, view_sheet to display progress, enrichment.get for final status. This is explicit when/when-not/alternative guidance.

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