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

Annotations already declare readOnlyHint/safe, so the bar is for added context, and this delivers: it discloses the return shape (recommended, CP range, W', fade estimate, confidence with reasons, hrZones with bounds), and critically warns that estimates are FLOORS and that confidence gates whether an update may be proposed, plus that a howToRead block must be read first.

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?

Long but front-loaded: the purpose and method come first, then usage, then scope, then a return-contract warning. Since there is no output schema, much of the length is load-bearing, though some density (CP range, W', fade, hrZones, howToRead all in one paragraph) could be trimmed.

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 fully carries the return-value burden by enumerating the fields and the howToRead/confidence contract, and it closes the scope gap for running. An agent has everything needed to call it and to interpret and report the result.

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 100%, so the schema already documents both parameters including the 'running returns guidance, not numbers' enum behavior and the default window. The description reinforces the 90-day default and cycling scope but adds no syntax or semantics beyond the schema, so the baseline 3 applies.

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+resource with method detail: estimates FTP/LTHR/max HR from ACTUAL synced rides via a mean-maximal power curve and Critical Power fit. It distinguishes itself from siblings by naming the scope (CYCLING ONLY) and explicitly ruling out running threshold pace, which separates it from estimate_cda and running-oriented tools.

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?

Gives explicit triggering conditions ('when heart rate sits under or over its zone on rides that felt right', 'when they ask whether their heart-rate zones are correct') and an anti-pattern correction ('that request is what the tool is for, not a reason to send them to a test'). It also names the correct alternative for out-of-scope cases (a recent race result or 30-min field test for runners).

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