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

Annotations only declare readOnlyHint and openWorldHint, yet the description adds substantial behavioral context beyond them: server-decided bucket grain from window length, the distinction between window-relative and UTC-calendar buckets, clipped first/last buckets, and the critical null-vs-measured-0 semantics plus degraded metrics being absent rather than zero. This is exactly the kind of disclosure that prevents misreading the result.

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 purpose before parameters and examples, and each block earns its place by resolving a real ambiguity (grain, clipping, null semantics). It is on the long side and the parameter prose is dense, but there is no filler or repetition.

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 restated, and the description instead supplies the interpretation rules that the output schema cannot convey (clipped buckets, null vs 0, degraded metrics). For a zero-required-param read-only overview tool, nothing an agent needs to invoke and correctly read it 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%, so the description must carry the full parameter burden and it does: workspace (id/name/org-name/workspace-name plus default and discovery via list_workspaces), hours (default 24, grain rules), minutes (for 'last 10 minutes', ignored when 0), breakdowns (default true), series (default false, verbose). Every parameter gets meaning and defaults beyond the bare JSON types.

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?

Names a specific verb and resource ('Aggregated health of a whole workspace over a time window') and then enumerates the concrete metrics returned (volume, cost, tokens, latency percentiles, TTFT, error rates, ranked breakdowns). It explicitly positions itself against siblings by framing the output as what you check 'before drilling into individual traces with list_agent_traces / get_agent_trace.' An agent can distinguish it from agent_traces_summary or user_activity_summary without opening a 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 an explicit usage trigger ('Use this to answer "how is my workspace doing"') and names the alternative tools (list_agent_traces / get_agent_trace) that handle the drill-down follow-up. It does not state exclusions relative to the other summary siblings (agent_traces_summary, user_activity_summary), so the when-not guidance is incomplete.

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