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

Beyond readOnlyHint/openWorldHint, it discloses two things annotations cannot: the result is aggregates only with no recipient data, and omitting campaign_ids silently scope-limits to the 25 newest non-draft/non-archived campaigns with a hint surfaced in `notes` — a truncation behavior an agent must know about. It also states the rate denominators (sent vs. delivered vs. reached leads), which determines whether the numbers are comparable.

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?

Structure is sound — return shape first, then parameters, then the sibling pointer — and the rate-denominator sentence earns its place. However, enumerating roughly twenty metric field names (sent, not_sent, delivered, bounced, ...) duplicates an output schema that already exists and bloats an otherwise dense block.

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?

Six optional parameters, no enums, an output schema, and read-only annotations — the description fills every gap that matters: time-window precedence, channel vocabulary, campaign scoping/truncation, workspace fallback, and the aggregate-only guarantee. Nothing an agent needs before calling 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 description coverage is 0%, yet all six parameters are explained: days as today−N, date_from/date_to with 'YYYY-MM-DD' format and UTC day semantics plus precedence over days, channel with valid values (email/linkedin/others) that the schema's bare string does not constrain, campaign_ids sourcing and default behavior, and workspace as a slug that is optional for single-workspace accounts.

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 first line names the exact resource and scope: outbound metrics per lemlist campaign for a period, plus a total row. It also distinguishes itself from the sibling lemlist_step_performance (per-step / A-B variants) by name, so an agent can route without opening the schemas.

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?

It points to lemlist_list_campaigns as the source of campaign_ids and to lemlist_step_performance when per-step or A/B breakdowns are wanted — both explicit alternative routing. It does not state a negative case (e.g. when to prefer list_campaigns alone or a reply-level tool), so it stops short of a full use/don't-use matrix.

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