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

Annotations already establish readOnly/idempotent/non-destructive, so the bar is lower. The description adds real context beyond them: results are 'retained' (retention-limited), pagination must continue through empty filtered pages, and rangeTraversed does not represent a snapshot or complete historical totals — a meaningful data-completeness caveat.

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 dense, front-loaded sentences with no filler. The second sentence is slightly jargon-heavy (rangeTraversed) without defining the term, but overall the length is appropriate for a list tool.

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 values needn't be explained, and annotations cover the safety profile. Still, a 9-parameter list tool with 0% schema coverage leaves the filters entirely unexplained, which is a substantial gap 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?

Schema description coverage is 0% across nine parameters, so the description must carry the load and does not. It references 'filtered pages' and 'nextCursor'/'rangeTraversed' but never documents the seven filter params (type, source, severity, receivedFrom/To, deliveryStatus) or clarifies that the input field is 'cursor'.

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 (read), resource (report summaries), and scope/ordering (retained, newest first), which distinguishes it from get_report by implication. However, it never names get_report or list_apps, so sibling differentiation is left to inference from the tool name.

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 pagination instruction ('Follow nextCursor even on empty filtered pages') is genuine when/how guidance for correct traversal. Beyond that, there is no statement of when to use this versus get_report, or what the filter parameters are for, so usage context is only partially covered.

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