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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered; the description still adds real value by disclosing that values are computed from the live event stream (freshness semantics) and by enumerating what is returned in the absence of an output schema. The closing 'Read-only' merely restates the annotation, but that is a minor redundancy rather than a contradiction.

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 the core purpose and the metric list, followed by two short qualifiers. Very little waste, though the trailing 'Read-only.' duplicates the annotation and could have been replaced with more useful information such as default window behaviour.

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 correctly takes on the job of listing the returned metrics, and it explains the data source. Remaining gaps — units/format of cycle-time percentiles, default time window, and whether a process needs to be mined/generated first — are modest but real for a metrics endpoint.

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 processId and the from/to fields are already documented; the description only echoes that the date window is optional and ISO-formatted. It does not clarify defaults, whether the window filters events or cases, or whether a missing window means all time, so it does not materially exceed 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 names the resource (a process), the source ('mined KPIs... computed from the live event stream'), and enumerates the metric families returned. It is clearly a metrics-read tool, but it never contrasts itself with near neighbours like get_sprint_metrics, list_process_insights, or run_process_insights, so an agent must infer the boundary.

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 only implied: '(Optimize)' and 'live event stream' hint at the mining context, and 'Optional from/to ISO date window' tells you the window is optional. There is no explicit statement of when to pick this over get_sprint_metrics or list_process_insights, and no prerequisites (e.g. does the process need mined event data first?).

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