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

readOnlyHint=true already tells the agent this is a safe read, so the bar is lower. The description adds that each attempt carries status, response code and body, which is useful output context, but says nothing about pagination behavior, ordering, or how attempts against failed vs. successful endpoints appear. Useful but not rich.

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?

Three short sentences: what it returns, why you'd call it, and the underlying REST route. Front-loaded with the verb and scope, zero filler, and the API path is compactly appended.

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?

With no output schema, the description usefully summarizes the return payload (status, response code, body) and the diagnostic intent. It omits pagination/iterator semantics for multi-page results, which the schema only partially implies, leaving a small gap for a 7-parameter listing 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 100% and all seven parameters (app_id, msg_id, limit, status, iterator, endpoint_id, status_code_class) are documented in the schema with ranges and enum meanings. The description adds no parameter-level detail beyond that, so the baseline 3 applies.

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 every delivery attempt Svix made for one message, across endpoints') and pins the scope to a single message, which cleanly separates it from the sibling svix_list_attempts_by_endpoint. The REST path (GET /api/v1/app/{app_id}/attempt/msg/{msg_id}) removes any residual 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?

"This is the tool for answering 'why did this webhook not arrive?'" gives a concrete diagnostic scenario for selecting it, which is stronger than implied usage. It never names the by-endpoint alternative or gives a when-not-to-use condition, so it falls short of the explicit routing seen in the top tier.

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