Sending sources

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

Annotations already cover safety (readOnly, non-destructive, open-world), so the description's job is added context — and it delivers: message-weighted counts, greatest-value-wins identity strings that are length-capped, volume-descending sort, a hard 50-row limit, and a 'truncated' flag. It does not mention auth scope or latency, but the return-behavior disclosure is unusually 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?

Four tight sentences, each carrying a distinct fact (granularity, weighting, identity capping, sort/limit). Information is front-loaded with the row shape. Slightly dense with no explicit lead verb, but 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?

With no output schema, the description must explain the shape of the return, and it does: one row per bucket, weighted counts, capped identity strings, sort order, row cap and truncation signal. Combined with a fully documented input schema and safety annotations, nothing essential 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 per the rubric the baseline is 3 and the schema already documents domain, group_by, day_after and day_before. The description confirms the source_ip default and clarifies that window bounds are inclusive via the schema rather than adding new syntax, so it adds only marginal value.

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 states the resource (sending IPs / autonomous systems / From domains) and the row granularity, plus sorting and the default grouping, so an agent can tell what this returns. It does not explicitly contrast itself with siblings like get_alignment_summary or query_records, but the construct is specific enough to be distinguished.

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?

There is no statement of when to use this tool versus alternatives such as list_aggregate_reports or query_records, and no prerequisites or exclusions. The default 30-day window and grouping behavior are only implied by the schema, not framed as usage guidance.

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