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

Adds substantial behavior beyond the annotations: 'A mutation executed status means executor acceptance, not proof of entity reconciliation', 'nextCursor repeats the same filters; since applies to the first page only', and the prompt-injection warning that event text is untrusted data. These are exactly the traps an agent would otherwise fall into.

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?

Very tight for the amount of information packed in — the scoping constraint leads, then routing, then semantics, then the safety caveat. The telegraphic semicolon style is dense but every clause is load-bearing and no sentence is redundant.

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 an 8-parameter read tool with no output schema, the description covers access requirements, parameter routing, pagination semantics, and data-trust caveats. The one gap is that it never characterizes what an event record looks like on return, which matters somewhat given there is no output schema to fall back on.

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?

With only 50% schema description coverage, the description carries real weight: it defines the mutationId vs sellerId+marketplaceId mutual exclusion, marks subjectId as optional exact SKU/ASIN, and explains cursor and since scoping. It doesn't cover limit's range/default, which the schema does, so this is compensation well done but not exhaustive.

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 opening ('Up to 30d authorized history') plus the closing 'This is a history read, not a subscription' make clear this retrieves historical events. The verb is implicit rather than stated outright — it relies on the annotations title 'Read event history' — and it never distinguishes itself from the sibling get_history, which is the closest alternative.

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?

Strong conditional routing: 'mutation.*: mutationId (own); no sellerId/marketplaceId/subjectId. Else sellerId+marketplaceId; optional subjectId' tells the agent exactly which parameter shapes apply to which event families. It also rules out a misuse ('not a subscription'). What's missing is any guidance on when to pick this over get_history or get_mutations.

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