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

Annotations already flag destructiveHint=true and openWorldHint=true, but the description adds cost consequences ('consumes the workspace's existing Leadbase credits'), irreversibility ('completed usage cannot be undone'), the destructive effect of each flag (replacing values, cancelling active work), and the crucial caveat that it returns accepted runs rather than completed results. It also supplies retry semantics for the non-idempotent case, which the idempotentHint=false annotation cannot convey on its own.

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 alternative, then ordered from cost warning to flag semantics to workflow and retry advice. Length is justified by the destructive, credit-consuming operation, though there is mild redundancy ('use only when the user explicitly requests that effect' restates the same rule twice, and irreversibility is stated in both the description and the schema).

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 complex, destructive, credit-spending mutation this covers everything an agent needs: cost, irreversibility, flag behavior, the distinction between accepted runs and completed results, the status/query follow-up path, and idempotency-key recovery after an interrupted response. An output schema exists, so return values need not be enumerated.

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 25%, so the description must carry more weight. It does clarify the operational meaning of force, replaceActiveTasks, and idempotencyKey (reuse after an ambiguous outcome), but it adds little beyond the schema text that already exists for those three and says nothing about the required applyThreshold parameter. Adequate but incomplete for the low coverage level.

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 ('Start paid web research for explicitly selected cells in an editable sheet') and immediately contrasts scope with the sibling sheets.enrich for one-column requests. An agent can distinguish this from sheets.enrich, sheets_enrich, and sheets_cancel_enrichment 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 ('For a simpler one-column request, use sheets.enrich'), prescribes default flag values for ordinary requests, and restricts force/replaceActiveTasks to explicit user request. It also routes follow-up reads to sheets.get_enrichment_status and sheets.query, so the when/when-not conditions are fully covered.

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