Get a time report

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

Beyond annotations (readOnlyHint=true, destructiveHint=false, openWorldHint=true), the description adds: response echoes the resolved date range, all durations are minutes, percentages are precomputed, and the tool normalizes answers. It also warns against inventing numbers, which is actionable behavioral guidance. No contradiction with annotations.

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?

The description is front-loaded with 'READ ONLY' and 'The single reporting tool', then systematically walks through every view, and ends with response-format guidance. Despite its length, every sentence provides unique value; there is no fluff. It is structured for quick scanning by an agent.

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?

Given 10 parameters, 9 views, no output schema, and rich behavioral expectations, the description covers everything an agent needs: view selection cues, date-range echo behavior, units, recomputation warnings, and explicit guidance on quoting ranges. It also clarifies edge cases like account-wide snapshots ignoring date ranges. Nothing critical 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?

The schema covers 100% of parameter descriptions, but the tool description adds significant meaning: it explains each view's use case, clarifies that groupBy applies only to summary, notes that presets are timezone-resolved, and highlights the schedule view's unique planned-vs-logged comparison. This goes well beyond the schema.

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 states the tool is the 'single reporting tool' with a clear verb (get) and resource (report), and distinguishes it from siblings by noting it routes to the right report and normalizes the answer. It also lists all views with their purposes, making it unmistakable.

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?

It explicitly explains when to use each view (e.g., 'day_total' for 'how did my week go', 'schedule' for planned vs logged) and instructs on how to quote the resolved date range to the user. It also says 'READ ONLY' and implies it is the go-to reporting tool, with no ambiguity about alternatives.

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