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

Annotations already flag destructive/inverse-of-readOnly behavior, but the description adds substantial context: it consumes Leadbase credits, completed usage cannot be undone, existing values/active cells are skipped, a new column is persisted before research starts, and it is asynchronous ('Returns accepted runs, not finished results'). The idempotency-key-on-retry instruction is equally non-obvious and valuable.

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 the purpose, then layered routing, constraints, and retry guidance — every sentence carries a distinct operational instruction. It is dense and longer than typical, but almost no sentence is redundant.

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 paid, async, destructive enrichment tool this covers everything an agent needs: scope, skip semantics, credit cost, irreversibility, alternative tools, and the follow-up path to status/query. An output schema exists, so return-value details need not be restated, and the description still correctly notes it returns accepted runs rather than results.

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 coverage is only 50%, and the description compensates by explaining the anyOf shape of 'column' (existing columnId with its configured question/type vs. a new name/question/type) and the exact semantic of omitting rowIds. The 'type' enum values themselves are documented only in the schema, so the description doesn't add on that axis.

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+resource+scope: 'Fill empty cells in one column of an editable sheet through paid web research using each row's existing context.' It also distinguishes itself from near-siblings (sheets.research, sheets.start_enrichment) that an agent would otherwise confuse it with.

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?

Explicit routing: use sheets.research for new result rows, sheets.start_enrichment for multi-column targets or replacement of existing values. It also states the omission rule for rowIds ('omit only when the user requests all existing rows') and names the follow-up tools (get_enrichment_status, query) for progress and results.

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