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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile needs no restating. The description adds real behavioral context beyond that: only non-deleted incidents are counted, 'Unacknowledged' is an organization-wide current count rather than a windowed one, acknowledgement/resolution times are minutes and null when unavailable, and the heatmap slot encoding is defined. The omission is what the response container looks like beyond these named fields, which keeps it below 5.

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?

Three sentences, front-loaded with the core purpose, followed by the counting semantics and then the encoding rules that an agent genuinely cannot get from structured fields. It is dense without being padded, though the second and third sentences pack several distinct facts that could be separated for easier parsing.

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 carries the burden of explaining return values and does so for the key fields: daily severity, up to six noisy services, two-hour heatmap cells with DayOfWeek/Slot encoding, up to ten assignee-based responders, and the organization-wide unacknowledged count. What remains uncovered is the overall response shape and cardinality limits for the severity series, but the semantic gaps that would cause a misread are closed.

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% and the single 'days' parameter is already fully documented, including the 1–365 clamping and the default of 7. The description restates the UTC-calendar-days-including-today meaning but adds no format or edge-case detail beyond the schema, so the baseline of 3 applies.

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 uses a specific verb and resource ('Report non-deleted organization incidents') and scopes it to UTC calendar days including today, so the agent knows this is an aggregated incident report rather than a raw list. However, it never distinguishes itself from close siblings such as incident_summary, incident_list, or monitor_report, so an agent must infer the boundary from the field inventory alone.

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 when-to-use guidance, no mention of alternatives, and no exclusion conditions. The text explains what the report contains but not the situation that should select this tool over incident_summary or incident_list, which is the main routing decision an agent faces here.

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