MTTR, MTTA, MTTD

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real behavioral value by disclosing what is computed (mean, median, p90, customer-detected share) and that severity is the default grouping — the latter appears nowhere in the schema. It stops short of explaining metric definitions or empty-period behavior, which keeps it below a 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?

Two tight sentences: the first defines the payload and its statistics, the second the grouping options. Metric names are front-loaded and there is no filler.

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 appropriately summarizes the return content (three metric families plus medians, p90 and customer-detected share), and the schema carries period and filter formats. Only the semantics of what MTTR/MTTA/MTTD measure in this system is left unstated, a minor but real gap.

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 a strong 75%, so the burden is light. The description still contributes the default grouping dimension ('severity (default)'), which the schema does not declare for group_by, and enumerates the same four group_by values, confirming the enum's meaning.

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 names the specific resource (incident response metrics), expands every acronym (MTTR/MTTA/MTTD), and enumerates the statistics returned plus the grouping dimensions. This clearly separates it from sibling metric tools like get_dora_metrics or get_defect_metrics, which cover different domains.

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?

Usage is implied by the metric names and the grouping sentence, but there is no explicit guidance on when to choose this over get_dora_metrics, get_kpi_trend or compare_periods, and no stated prerequisites or exclusions. An agent can infer intent from the domain, but must reason about sibling selection itself.

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