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

Annotations already declare readOnlyHint and idempotentHint, so the agent knows it's a safe read. The description adds meaningful behavioral detail beyond annotations: 'Only completed sets count' and metric-specific semantics (acute:chronic ratio thresholds, per-muscle freshness, correlate pairing). This goes beyond the structured safety hints without contradicting them.

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 two sentences, front-loaded with the main purpose, and every clause earns its place. It packs essential details (metric selection, specific thresholds, and counting rule) without any fluff 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?

Given 14 parameters, several enums, and no output schema, the description effectively conveys the core selection mechanism and explains the most complex metrics. It doesn't cover all metrics, but the schema handles those parameter descriptions. The addition of the 'only completed sets' rule adds cross-cutting context. A little more guidance on date-range or grouping could improve it, but it's not necessary due to schema support.

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 86%, leaving a high baseline. The description adds value by explaining semantic nuances for several enum values of `metric` (training_load, muscle_recovery, correlate) and clarifies data scoping ('Only completed sets count'). This supplements the schema's brief parameter descriptions.

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 clearly states the tool's function: 'Any progression metric for the current user — pick one in `metric`.' It identifies the resource (progression metrics) and the action (retrieve), and differentiates itself from siblings like get_muscle_recovery by covering all metrics in one tool. The scope is well-defined (current user) and the examples add specificity.

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?

The description provides useful context on how metrics work (e.g., training_load thresholds, correlate requires two metrics) but does not explicitly state when to use this tool vs alternatives like get_muscle_recovery or get_body_metrics. Usage is implied rather than directly guided, so it lacks clear when-not-to-use guidance.

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