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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds the non-obvious access constraint (admin only) and the concrete pagination loop seeding 'cursor' from the previous 'nextCursor'. It stops short of describing ordering, result volume, or what an empty list means, keeping it off a 5.

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?

Two short sentences with the access restriction and scope front-loaded, then pagination. No filler, and no sentence that fails to earn its place.

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?

A return schema exists, so return values need not be explained, and the admin/pagination essentials are present. The gaps are the undocumented 'limit' behavior and the unexplained relationship of 'account_id' to the 'selected' account, which matter for correct invocation on a 4-parameter tool.

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% across four parameters, so the description carries the full burden. It explains the 'domain' filter and the 'cursor' pagination mechanic usefully, but says nothing about 'limit' (default 100, no stated maximum) and leaves 'account_id' ambiguous even though the phrase 'selected middleware account' gestures at it.

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 and resource ('list persisted middleware transactions') and scopes it to the selected middleware account with an optional domain filter. This distinguishes it reasonably well from middleware_get_transaction, though it never names that sibling explicitly.

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 'Middleware admin only' qualifier and the domain-filter note imply when to reach for it, and the pagination hint tells the agent how to continue a listing. However, there is no explicit guidance on when to pick this versus middleware_get_transaction or middleware_get_capabilities, so the agent must infer the boundary.

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