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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description layers on substantial behavioral detail: de-duplicated counts with welcome/birthday/transactional excluded, a two-subject-line cap, the sends_with_subject_in_signal explanation for withheld subjects, local calendar dates, and a two-year period ceiling. This is exactly the kind of beyond-annotation context the dimension rewards.

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?

Purpose and scope are front-loaded, and the dense multi-clause sentences each carry distinct rules rather than filler. It runs long, and the illustrative example questions plus the repeat of return contents could be trimmed, but nothing is genuinely wasted.

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 need not be re-explained, yet the description still frames them usefully (count, per-send dates up to 31 days, subject-line limit) and covers periods, dedup rules, market fallback and geographies. An agent has everything needed to call it correctly.

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, but the description adds real semantics: it explains that omitting market yields one result per tracked market, and it spells out how to resolve relative dates into YYYY-MM-DD ("last week" = previous Monday–Sunday, "recently" = last 14 days). Those rules are not derivable from the schema patterns.

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 (how many marketing emails a brand sent, and when) plus the observing source and its geographic coverage. The scope is so precisely bounded that an agent can distinguish it from find_brands and get_brand_summary without opening either 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 concrete trigger phrasing ("How many emails did Newport send in August 2026?") and explicit when-not guidance (no open/click/revenue data, no full campaigns, other subject lines or creative analysis available through this tool). It routes the agent onward to details_url for the full campaigns, though it never names the sibling tools as alternatives, which keeps it short of a 5.

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