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

Annotations already declare readOnly/idempotent/non-destructive, so the description only adds ordering and a catch-up framing. It does not describe pagination or response shape, but for a read-only list that is acceptable.

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 sentences, front-loaded with the core purpose, and the catch-up instruction is compact. No filler.

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 listing tool with strong annotations and 80% schema coverage, it gives purpose, ordering, and a key use case. It could mention pagination/next_cursor explicitly, but the schema's cursor parameter already hints at it.

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 covers 80% of parameters with descriptions, so baseline is 3; the description adds meaningful guidance by pointing to the 'failed'/'dead' status values for catch-up. It does not add to brand/since/cursor, but schema already covers those.

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 resource ('delivery attempts for a brand') and ordering ('newest first'), and adds an outage catch-up use case. It does not explicitly name siblings like delivery_replay, and 'replay what you missed' blurs whether this tool also replays.

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?

Explicitly says to use it after an outage and to filter by status 'failed' or 'dead'. It does not name alternative tools or state when not to use, but the context is clear enough for an agent to choose it for catch-up listing.

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