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

Annotations already establish readOnly/non-destructive/non-open-world, so the description is free to add value beyond them - and it does: it discloses the sort tie-breaker ('Equal creation times use descending ID order'), the pagination loop protocol (continue via meta.next_offset with the same filters, stop when null), and the important caveat that 'Results can change between requests', implying offset paging over a live set. These are operational traits an agent cannot infer from 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?

Roughly four tight sentences, front-loaded with the verb, resource and ordering, then use cases, then pagination mechanics. No filler or restatement of the title; every clause conveys a fact an agent needs.

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?

An output schema exists, so return shape needn't be described, and the description still covers the pieces it must: eligibility scope (whole account), ordering and tie-break, defaults and maximums, and the full pagination termination rule. Nothing required to call this list tool correctly is missing.

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 coverage is 100%, so the baseline is 3. The description goes slightly beyond by spelling out the continuation contract between 'offset' and 'meta.next_offset' (same filters preserved, terminate on null) and by stating defaults and the 100 cap in one place, though it repeats values already present in the schema and adds nothing specific about tags/tag_mode semantics.

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 Push Notification history for the account') plus the ordering ('newest first'), and explicitly names the sibling get_push_notification as the single-item alternative. An agent can distinguish it from list_channels, list_tags, and get_push_notification without opening any schema.

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?

Gives three concrete use cases (review what was sent, find a notification's public_id, filter by Tags) and an explicit routing rule: for one known notification use get_push_notification. That is a when-to-use plus a named alternative, not an implied one.

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