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

Far exceeds what the annotations declare (destructive/idempotent/openWorld). It discloses that jobs run in the background, that Leadbase credits are consumed and completed usage is irreversible, that it does not send messages/purchase/execute arbitrary actions, that unknowns stay null/empty and fewer matches is a partial result, and that the call returns immediately after atomic batch acceptance. This is exactly the behavioral context an agent needs before committing spend.

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 and the sibling alternative, then lifecycle, billing and recovery in a dense sequence. It is long, but nearly every sentence adds operational information (idempotency recovery, polling, credits) rather than padding, so the length is largely justified.

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?

Given a nested, credit-consuming, asynchronous batch tool with an output schema present, the description covers the full lifecycle: submission, atomic acceptance, polling via enrichment.get, billing settlement, and failure recovery. Nothing needed to invoke or follow up on it correctly 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?

Schema description coverage is only 50%, so the description must carry weight, and it does: it explains that each item needs a unique id, task-relevant known facts, a question, and a typed output that is either a scalar or a list with named scalar fields and maxItems. It omits detail on the optional toolId field, so it is strong but not exhaustive.

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 ('research factual questions about companies, people, products or public web content for 1-100 independent inputs') and immediately contrasts itself with the sibling sheets.research. An agent can distinguish it from all the sheets_* enrichment siblings without opening any 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?

Explicitly names the alternative ('Use sheets.research when the user wants a saved list'), gives the polling follow-up (enrichment.get with batchId until terminal and billingStatus settled), and prescribes exact recovery behavior for interrupted submissions (reuse idempotencyKey with unchanged items, never a new key). When-to-use and when-not-to-use are both present.

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