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

Annotations declare readOnlyHint=true and destructiveHint=false, but the description adds substantial behavioral context: silent downgrade of week/month to day on free plans with planGated=true, dense zero-filled buckets, and scope-dependent latency series keys (relayP50 vs targetP50 vs p50) without blending. This goes well beyond the safety hints and fully discloses edge-case behavior.

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?

Though lengthy, the description is front-loaded with the core purpose and each subsequent sentence earns its place: scoping rules, plan restrictions, response shape, and dense-series detail are all meaningful. The structure uses semicolons and clear delimiter ('By default...', 'pass...', 'Returns...') to keep it organized without redundancy.

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 takes full responsibility for explaining return values and does so thoroughly: lists the response keys, explains latency series variants by scope, notes planGated semantics, and clarifies that arrays are dense. Combined with the parameter and safety details, the description is complete for a 3-parameter, no-output-schema 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 100%, so the baseline is 3. The description enriches this by clarifying the mutual exclusivity of targetId/endpointId, default scope, and the plan-gating behavior of window. It also ties each parameter to a diagnostic question ('which target is degraded?'), adding practical semantics beyond the schema's field-level explanations.

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 opens with a specific verb and resource: 'Aggregate request metrics for this project over a time window' and lists the exact metrics (volume, error rate, p50/p95/p99 latency) and purpose (bucketed for charting). It clearly distinguishes itself from sibling tools like list_requests by focusing on aggregation and time-window bucketing.

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 description provides clear context for when to use each parameter: default behavior covers inbound requests, targetId slices outbound target degradation, endpointId slices inbound endpoint health, and 'Pass at most one of targetId / endpointId' is an explicit constraint. However, it does not name alternative tools for comparison (e.g., when to use list_requests instead), so it falls short of the explicit when-not/alternatives bar.

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