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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the write profile is known; the description adds real value by scoping the write ('This never mutates TikTok', it only persists decisions/notifications and may update an existing evaluation) and by bounding behavior ('budget scaling is capped at 30 percent and remains only a recommendation'). What gets overwritten on an 'existing evaluation' is only hinted at, but this is well beyond the annotations.

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 the core verb and the strongest constraint ('never mutates TikTok') in the first two sentences, and the trailing paragraph on persistence is short. There is mild redundancy between 'persist bounded read-only recommendations' and 'Persists decisions and notifications', 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 9-parameter tool with no output schema and 0% schema description coverage, the description covers the behavioral contract well but under-serves the inputs: over half the parameters are unexplained, and there is no mention of what the persisted evaluation or notifications look like to the caller. Adequate but with clear gaps.

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 0%, so the description must carry parameter meaning. It explains group_by's two valid values, the advertiser-currency semantics and pause-conditionality of max_cost_without_conversion, and the 30% ceiling relevant to budget_increase_percent, but leaves advertiser_id, target_roas, min_conversions, the date range, and connection_context completely undocumented. Partial compensation only.

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 names a specific verb and resource ('Evaluate one owned TikTok advertiser... and persist bounded read-only recommendations') and explicitly distinguishes its scope from the Meta-side siblings ('do not use Meta adset fields'). An agent can tell this apart from optimization_list_decisions, optimization_dismiss_decision, and optimization_prepare_action.

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 supplies call-level rules ('Choose native campaign or ad_group', a pause candidate requires max_cost_without_conversion) but never states when to use this tool versus the sibling optimization_prepare_action or dismiss/list tools, nor what prerequisite state ('complete, fresh cached ledger evidence') must be satisfied first. Usage is implied rather than routed.

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