mailkite_retry_deliveries

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

Annotations only indicate readOnlyHint=false, idempotentHint=false, destructiveHint=false, which convey little about side effects. The description adds crucial behavior: always returns HTTP 200 with a per-id results array, instructs to branch on 'ok' and 'results' rather than status, explains that unowned ids are skipped with reason 'not_found' (mirroring the 404 of the single endpoint), and states the auth requirement (management session token). This is rich context 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?

Every sentence earns its place: purpose, parameter semantics, limit, response behavior, error handling, and auth. Information is front-loaded with the core purpose and then logically sequenced. Despite being detailed, it remains tight and readable with no repetition.

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?

Given no output schema, the description compensates by describing the response shape (results array with per-id outcomes) and the 'ok' field. It covers edge cases (not_found, no_delivery), the interaction of parameters, and the required token. An agent has everything needed to call this correctly, including how to handle partial failures.

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?

The schema already provides descriptions for all three parameters (100% coverage), so the baseline is 3. The description adds value by clarifying how parameters combine ('they combine'), the 50-id cap, and the server-side expansion of threadIds. It also notes the 'no_delivery' skip reason for messageIds. This goes beyond the schema, warranting a 4.

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 opens with a specific verb ('Replay') and resource ('webhook deliveries'), explicitly calling itself 'the bulk form of retryDelivery,' which distinguishes it from the single-delivery sibling. It states exactly what it does and how it relates to an alternative, leaving no ambiguity.

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 names the single-delivery tool (retryDelivery) as the non-bulk alternative and explains when to use this one (bulk selection). It also gives explicit guidance on combining id types, the 50-id limit, and batching larger selections sequentially. This is actionable and prevents misuse.

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