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

Annotations already declare readOnly/openWorld=false/destructive=false, so safety is covered; the description adds substantive behavior beyond that: it is not a live write readback, changes are detected regardless of console vs API origin, and the changes view requires two snapshots to produce a delta. It stops short of auth requirements or freshness/latency specifics, so it is strong but not exhaustive.

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 'Use for...' and every sentence carries information (purpose, view semantics, caveat, exclusions). It is dense — three long sentences with parentheticals — but no clause is padding, just slightly heavier than strictly necessary.

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?

With 14 parameters, an output schema present, and annotations covering the safety profile, the description supplies everything else an agent needs: purpose, view routing, data freshness caveat, and explicit exclusions (no metrics, no live write readback). Return values are correctly left to the output schema.

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 100%, so the baseline is 3, but the description adds meaning beyond the schema for the key 'view' parameter by explaining what each mode returns at a data level (state, budget, bidding, portfolio, placement bid adjustment) and how the changes mode behaves. The two-day delta caveat is operational semantics not present in the schema.

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+resource ('Sponsored Products campaign settings snapshots from the campaign_snapshots sync') and immediately distinguishes itself from the sibling performance tools by declaring what it does not return. An agent can separate it from get_campaign_performance and get_sp_entities_live 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 routes between the two views (history = daily state rows; changes = deltas) and names the alternative to use for metrics ('use get_campaign_performance for metrics'). It also states the precondition for the changes view ('needs at least two days of snapshots to show a delta'), which is a genuine when-to-use constraint.

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