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

The description goes beyond the idempotent/read-only annotations by revealing the dynamic behavior of the response (pending -> eventual statuses), the caveat about feed-only sends having no rows, and the pagination mechanism (nextCursor). This adds helpful context for an agent, though the annotations already cover idempotency and read-only safety, so the description adds value but doesn't disclose every possible behavior.

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?

The description is concise but packs a lot of essential info in two sentences. It starts with the core purpose, then explains the response contents, adds a timing tip, a special case, and pagination guidance. It is efficient without being sparse, though it could be slightly more structured (e.g., bullet points) but that's not required. It's a good length.

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 status tool with only 3 parameters (well-documented in schema) and no output schema, the description covers the response structure, timing considerations, special cases, and pagination. This makes it complete enough for an agent to call correctly. The only minor gap is lack of explicit mention of what 'provider errors' look like, but that's not essential for correct invocation.

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 input schema already has 100% coverage with descriptions for each parameter: `sendId` is explained (returned by send_notification), `limit` has defaults and max, and `cursor` is tied to `nextCursor`. The description reinforces pagination via the `nextCursor` but does not add much extra meaning beyond the schema. Baseline is 3 due to high coverage.

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 clearly states the tool's purpose with a specific verb ('get') and resource ('send status'), and provides detailed details on the response: aggregate counts per status, per-recipient rows with provider errors. It distinguishes itself from other tools by focusing on delivery status, and the HTTP method and endpoint are stated 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 description provides clear guidance on when to use the tool: to check delivery status after sending a notification. It notes that rows may be 'pending' initially and suggests checking again after a few seconds, offering practical usage tips. It also mentions that feed-only sends have no rows retreating directly from the tool's behavior, but does not explicitly state when not to use it or mention alternatives, so it's 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.