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

The readOnlyHint annotation already tells the agent this is a safe, non-mutating call. The description adds that the covered tasks are long-running bulk operations (replays, expunges, imports) whose status is tracked, which is useful context, but it says nothing about polling cadence or whether results are eventually consistent.

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 compact sentences that front-load purpose and then usage, with zero redundancy. The trailing 'Svix REST: GET /api/v1/background-task' line is reference detail rather than instruction, but it is short and harmless.

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 read-only, four-optional-parameter list tool with full schema coverage and no output schema, the description supplies the necessary scope and trigger context. The only gap is behavior around paging results, which the schema's iterator field largely covers.

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 100%, so task, limit, status, and iterator are already fully documented in the schema, including the enum values and cursor semantics. The description only adds the parenthetical notion that status is part of the view; baseline 3 is appropriate when the schema carries the parameter burden.

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 Svix background tasks') and clarifies scope with concrete examples ('bulk replays, expunges, imports') plus what is returned ('with their status'). No sibling tool covers background tasks, so the agent can distinguish it immediately from the list_* message/endpoint/attempt tools.

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?

'Use it to follow up a recover or replay' gives a clear triggering context that ties this tool to sibling operations like svix_recover_endpoint. It stops short of stating when not to use it (e.g. to inspect individual deliveries, use svix_list_attempts_by_message), so it is not a full 5.

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