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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the '[read]' prefix is redundant. The description does add genuinely behavioral context — the default scope is every form of the merchant when no identifier is given — but says nothing about aggregation lag, rate limits, or whether the comparison period is automatically derived.

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?

Front-loaded with the read marker and the report's contents, then the parameter rules — an efficient ordering with almost no filler. The compressed parenthetical 'by `lead_id` or `lead_uuid`' is slightly awkward to parse, which keeps it just short of ideal.

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 and no schema descriptions, the description carries the burden of telling the agent what comes back, and listing the four report dimensions (daily deltas, UTM sources, board stage, conversions) largely does that. It leaves the response shape and period-comparison semantics implicit, which is the remaining gap for a reporting tool.

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% (bare integers/strings with defaults), so the description must compensate, and it does: `days` is constrained to 7, 28 or 90 — an enum the schema does not encode — and lead_id/lead_uuid are described as mutually-alternative selectors with a defined omit-both default. It stops short of stating precedence when both identifiers are supplied.

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 ([read] Lead form submissions report) and then enumerates the exact content produced: daily counts vs. previous period, UTM sources, follow-up board position, and customer conversions. This is clearly distinguishable from siblings like list_lead_submits (raw records) or get_utm_sources_report (single-dimension breakdown).

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 scoping guidance is good — 'omit both for every form of the merchant' and 'lead_id narrows it to one form' tell the agent how to widen or narrow scope. However, it never names an alternative tool or states when to prefer this report over get_utm_sources_report, get_metric_report, or list_lead_submits; usage is only implied by the report contents.

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