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

Annotations only give destructiveHint=true, and the description earns that destructiveness: delete makes 'the leg revert to statsSource 'manual', retaining its last computed stats.' It also discloses the distinct inline (5 Mi UTF-16 code units) versus server-side (32 MB / 75,000 trackpoints) pipeline caps and that reprocess runs 'at the current pipeline version.' These are behaviors the annotations cannot convey.

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 action is front-loaded, but the definition is one very long sentence with heavily nested parentheticals that bury the actionable content in the middle. The trailing sentence about timestamps, distances, and durations is dead weight here — none of those appear in this tool's input schema and there is no output schema to annotate.

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 multi-mode write tool with no output schema and destructive annotations, the description covers caps, failure paths, and the post-delete state, which is most of what an agent needs. The remaining gaps are the unexplained maxSpeedKn semantics and no mention of what a successful import/reprocess returns.

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 100% schema coverage the baseline is 3, but the description adds real meaning: it clarifies that maxLength counts UTF-16 code units (so the 5 Mi cap is not a byte count), and documents ID format, UTC ISO 8601 timestamps, and integer meters/seconds. The one gap is maxSpeedKn — its unit and purpose (knots, filtering/handling fast segments) are never explained.

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 first clause names a specific verb and resource — 'Change a leg's GPX track' — and then enumerates the three modes (import, reprocess, delete), so an agent knows exactly what the tool does. It is distinguishable from the read sibling track_read by the write verb, though it never names a sibling to route against explicitly.

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 clearly explains which mode applies and, importantly, an alternative path: files over the inline cap 'go through the REST upload route instead' and over the point cap must be split or simplified. It stops short of stating tool-level when-not-to-use or naming a specific sibling tool for the REST route, so it falls just short of a 5.

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