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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuine behavioral context beyond that: it explains the fallback to a suggested load when no test exists, that hand-written answers are merged with auto-detected ones, and points to howToRead for interpretation. It does not describe pagination or ordering, keeping it short of a 5.

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?

It leads with the resource and folds parameters into the end, which is good front-loading, but the middle is overstuffed with jargon and parenthetical references (profile fatigueTest / fatigueTestRun, log_sft_answers, howToRead) that make it hard to parse in one read. Some clauses could be trimmed without losing meaning.

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 compensates by enumerating what each test entry contains (load, HR vs baseline, HR drop, answers, check-in) and how lower HR can signal fatigue. This is close to complete; a note on ordering or result limits would make it fully sufficient.

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 baseline is 3, but the description adds real meaning: `sport` picks the bike (watts) vs run (pace) test, `weeks` looks back with default 12, and `suggest` is for deriving watts from their own riding. These go beyond the schema's literal text and clarify intent.

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 concrete verb and resource — retrieves the athlete's SFT (fatigue test) log — and specifies the source (auto-detected tests plus hand-written log_sft_answers entries). It is dense with domain jargon (SFT, profile fatigueTest, howToRead), which slightly obscures the plain purpose, but the resource is unambiguous and distinguishes it from generic activity/readiness 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?

Implies when behavior changes (proposes the protocol's load when no test is set up or when suggest:true, and suggest is for 'what watts should my test be' or a new season). However, it never explicitly says when to call this versus siblings like get_readiness or get_metric_history, leaving the routing to inference.

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