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

Annotations declare openWorldHint=true, readOnlyHint=false and destructiveHint=false; the description goes further by clarifying that nothing spends while paused, that a preview is returned without confirm, and that only draftable findings qualify. It still doesn't say whether repeated calls create duplicate drafts (idempotentHint=false hints at this, but the description never addresses re-invocation or auth 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?

Short, front-loaded, and every sentence carries a distinct constraint (purpose, no-spend, eligibility, user consent). Slightly dense run-on phrasing but no filler.

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 5-parameter mutation tool with no output schema, the description covers the safety profile, consent requirement and eligibility gate. What remains thin is the shape of the returned preview and whether a second send duplicates the first draft.

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 80%, so the baseline is 3, but the description adds real meaning: the confirm flag's false branch (preview, no send) and the fact that item_key must be a draftable finding from get_today. It does not explain the objective or daily_budget semantics beyond the schema, hence not a 5.

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 precise verb and destination resource ('send one finding from get_today as a PAUSED campaign and ad set on the brand's own Meta ad account') and names the sibling it draws from. It is clearly distinguishable from the other get_* analysis tools in the sibling list.

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 says 'Only use this when the user has clearly asked for it, and pass confirm true,' and states the ghost path ('without confirm it returns a preview and sends nothing'). It also gates eligibility ('only findings marked draftable can be sent'), so the agent knows the precondition.

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