custom_metrics_read

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

Annotations already declare readOnly, idempotent, and non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond that: default 30-day window, unix-second timestamps, and that includeTimeSeries adds per-day points. It does not mention pagination behavior or response envelope shape, but the added context is real.

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?

A single dense paragraph that front-loads the core purpose, then the action list, then time-range and time-series defaults. Every clause carries information. Slightly compressed with parenthetical nesting, but no wasted sentences.

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?

For a 10-parameter, four-action tool with no output schema, the description does most of the needed work: it defines each action, the time-window defaults, and what the aggregated payloads contain. The remaining gap is that it never sketches what 'list' or 'get' return, which matters slightly more given no output schema.

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?

With 70% schema coverage the baseline is 3, and the description earns above that by explaining aggregation semantics per type ('averages/sums for numbers, counts for boolean/enum/string') and clarifying that 'data' takes the metric key rather than the id. It adds no detail on the uncovered parameters (includeTimeSeries flag semantics are only partly explained, startAfterId ignored).

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 the custom analytics metrics of an agent') and even defines what a custom metric is with concrete examples. It enumerates the four actions, so an agent knows the tool is a multi-action reader. It stops short of naming custom_metrics_write as the mutation counterpart, so sibling differentiation relies on the tool name 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?

Each action is scoped inline: 'list', 'get (metricId)', 'data (aggregated values for one metricKey...)', 'all_data (same for every metric)'. That gives clear conditions for choosing among the four modes. It does not explicitly state when not to use this tool or point to a sibling for metric creation/editing.

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