Edit the pricing plan

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

Annotations already declare non-read-only, idempotent, non-destructive and closed-world, but the description adds genuinely new behavior: the write is confined to a saved plan rather than the store, and the tool returns the updated get_pricing summary. It also discloses the asymmetric subscriber rule (decreases can reach existing subscribers, increases never do) and that startDate is App Store only — details the annotations cannot convey.

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?

Nearly every clause carries information, and the store-write disclaimer is front-loaded, but the entire body is one very long sentence laced with parentheticals, which makes it hard to scan. Splitting the mutation semantics from the parameter legend would preserve the content while improving retrievability.

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 12-parameter mutation tool with nested objects and no output schema, the description covers the operation set, the method vocabulary, the return value (updated get_pricing summary) and platform-specific caveats. It stops short of explaining interaction between parameters (e.g. whether override and resetOverrides can be combined, or what happens if select is omitted alongside other edits).

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 baseline is 3, but the description adds real meaning beyond the schema by decoding the opaque enum values (tiers = five income tiers, purchasing_power = GNI PPP, income = GNI Atlas, blended = both, equal = store conversion). The floor/ceiling ranges and default for keepExistingPrices merely restate the schema, capping this below 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?

The description states a specific verb and resource ("Change the saved pricing plan") and immediately scopes it with "nothing is written to the store", which separates it from the publishing sibling publish_pricing. It then enumerates every editable facet (selection, method, floor/ceiling, endings, base price, override/reset, start date, subscriber handling, IAP timing), so an agent knows exactly what the tool mutates.

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?

The parenthetical "nothing is written to the store" implicitly tells the agent this is the draft/plan step that must precede publishing, and the return note points at get_pricing for verification. It does not, however, name publish_pricing explicitly as the follow-up or state any preconditions (e.g. that products must already exist), so the routing is inferable rather than spelled out.

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