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

Annotations already declare readOnlyHint/non-destructive, so the description focuses on behavior beyond safety: server-computed curve requiring the athlete's own PMC time constants, default windowing, and that real is bounded to today. Doesn't cover output shape, but output schema exists.

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 purpose sentence followed by per-parameter blocks and a return-field glossary. Every sentence adds information; the PMC explanation justifies why the curve isn't recomputed client-side.

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 4-param read tool with an output schema and annotations, the description covers the semantic distinctions (real vs planned, own vs managed athlete, date windowing) and explains what each returned field means, which the output schema alone wouldn't interpret.

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 0%, so the description carries the full burden and does: documents mode values and defaults, date format 'YYYY-MM-DD' with default 90 days, and the usr_… handle format for athlete sourced from list_athletes. This compensates fully for the bare 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 (read) and resource (training-load curve, Coggan fitness/fatigue/form) and names the metric families it returns. It's distinguishable from siblings like get_stats_chart and get_training by naming the concrete curve concept.

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?

Explicitly explains the two temporal halves: 'real' (realized curve, bounded to today, default) vs 'planned' (forward projection after today), with the rule 'ask for the one the question is about'. Also tells when to omit athlete (read your own) and when to omit dates (default 90-day window).

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