Import daily campaign metrics (CSV or rows) into a manual, no-API connection

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

Annotations only say readOnlyHint=false and openWorldHint=true. The description adds genuinely non-obvious behavior: the call is destructive-on-confirm with no server-side dry run, and it degrades to a request preview when confirm is absent. It does not cover partial-failure behavior, sync vs async, or idempotency semantics, which are relevant for a bulk mutation.

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?

Two tight sentences: purpose and endpoint first, then the write-safety warning. Nothing is repeated and the critical gating constraint is not buried.

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 nested-body mutation with no output schema, the description supplies the safety model an agent most needs before calling. It could say more about what the response contains (import job, counts, rejected rows) and about large-import behavior, but it is broadly sufficient.

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 75% and the nested body already documents csv-or-rows exclusivity, row requirements, and confirm's preview behavior. The description only restates the CSV/rows choice and confirm gating, adding no format or sizing detail beyond the schema. Baseline 3 applies.

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 (Import), resource (daily campaign metrics), and target (a manual, no-API connection), plus the underlying endpoint. The qualifier 'manual, no-API connection' separates it from OAuth/credential-based connection siblings, though no sibling such as revenue_importCsv or tracking_ingest is named explicitly.

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?

Gives one concrete usage rule: the write is not executed unless confirm: true, and without it a preview is returned. That is a real precondition, but there is no guidance on choosing this over adjacent ingestion tools (revenue_importCsv, tracking_ingest) or on when a manual connection is the right target.

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