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

Annotations already declare read-only, idempotent, non-destructive, and closed-world behavior. The description adds meaningful window validation rules and the special zero/missing baseline percentage-delta behavior, though it does not discuss error handling or auth requirements.

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 dense sentences front-load the comparison and window rules, with every clause adding a constraint or edge case. 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?

Because an output schema exists, return values need not be explained. The description covers the critical window comparison constraints and baseline edge case, but does not elaborate on filter arrays or kind/metric defaults, leaving some schema elements to structural inference.

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 low, so the description must carry parameter meaning. It explains the current/baseline window semantics, their shared filters, and the zero-baseline case well; however, kind and metric are left mostly to their enum values and defaults in 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?

States a specific verb and resource: compare equal-length, non-overlapping half-open UTC windows with identical filters. This is clearly distinct from sibling tools like get_run_stats or list_runs, and an agent can identify the operation without opening the 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?

Provides valid-window constraints (equal-length, non-overlapping, adjacent allowed) and an edge case for zero/missing baseline, but does not say when to prefer this tool over sibling analytics tools or when comparison is inappropriate. Usage is implied rather than explicitly guided.

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