set_profile

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

readOnlyHint=false only tells the agent this mutates; the description goes further by disclosing the analysis re-run side effect and, importantly, the destructive clearing semantics of the value "none" (which fields get wiped). That is real behavioral context beyond the annotation, though it omits permissions/error behavior.

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 with the core action, then a dense but necessary key reference, then the clearing rule. Every item earns its place, though the key enumeration is compact to the point of being list-like.

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 2-param mutation tool with no output schema and no schema descriptions, the description supplies the missing parameter semantics and clearing behavior. It stops short of explaining return values or what happens on invalid keys, but is otherwise sufficient to call the tool correctly.

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?

With 0% schema description coverage, the description carries the full burden and does so well: it enumerates every valid key and pins down value formats (race_date as YYYY-MM-DD, units as metric/imperial, timezone as an IANA name, goals as a list of strings, hrmax_override as number-or-numeric-string) plus the special "none" value. This adds substantial meaning the generic key/value schema lacks.

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 states a specific verb+resource ("Change a profile value") and adds a distinctive behavioral consequence ("re-run the analysis"). Enumerating the valid keys makes the tool's scope unambiguous and clearly separates it from the get_*/log_* siblings.

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?

It lists valid keys and formats, which implies usage, but never says when to reach for this tool versus the other profile/data tools or what prerequisites exist. The usage is inferable but not stated.

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