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

Adds substantial behavior beyond the annotations (destructive, idempotent, openWorld): paid research consumes Leadbase credits without another call, only empty cells with usable context are researched and existing values are preserved, disabling does not cancel or reverse started runs, and it requires edit access plus the current column version. This is exactly the extra context a mutation tool needs.

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?

Dense but front-loaded: the core enable/disable action and its credit implications lead, with prerequisites and idempotency guidance trailing. Every sentence carries operational meaning, though the paragraph is long and could be broken up for scanning.

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 destructive, credit-consuming mutation with an output schema present, the description covers cost, eligibility, irreversibility of disabling, access/version prerequisites, idempotency recovery, and where to inspect status or cancel. Nothing an agent needs to call it safely is missing.

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 50% schema coverage, the description meaningfully compensates: it explains requiredColumnIds as all-must-be-present prerequisites and instructs using [] when none are requested, and explains the idempotencyKey reuse rule and expectedColumnVersion requirement. The semantics of enabled and the version param are reinforced in prose.

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 states a specific verb pair (enable/disable) and resource (ongoing, paid web research for one sheet column using its configured question and type). The 'ongoing/automatic' framing separates it from one-off siblings like sheets_enrich and sheets_start_enrichment without needing the 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?

It gives an explicit usage condition ('Enable only when the user requests automatic research') and routes the agent to sheets.get_enrichment_status for runs/costs and sheets.cancel_enrichment for cancelling. It stops short of explicitly contrasting with the sibling one-time enrichment tools, so the routing is clear but not exhaustive.

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