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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description adds substantive context on top: a consent requirement, a confirmation handshake before invocation, and a partial-update guarantee that unspecified fields are untouched. It still doesn't say what the response contains beyond serviceAnnouncements or how failures present, but this is well above the annotation baseline.

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?

Three front-loaded sentences with the confirmation requirement placed ahead of the announcement directive, and no filler. The serviceAnnouncements sentence is operationally verbose but appears to be required output-handling behavior rather than padding.

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 destructive three-parameter mutation with no output schema, the description covers the gating flow, the partial-update contract, and the one response element the agent must surface. Remaining gaps — return shape beyond serviceAnnouncements and error behavior — are modest given the annotations already encode the safety profile.

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 33%, with only activityId documented in-schema, so the description carries some burden. It clarifies that confirmed=true follows a user confirmation (adding meaning beyond the const:true constraint) and that only requested fields in the nested changes object are applied, but it adds nothing about the four updatable fields.

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?

Names a specific verb+resource ("Update ... activity fields") and constrains scope with "only activity fields you explicitly asked to change," which signals partial-update semantics distinct from garmin_create_activity or garmin_delete_activity. It stops short of naming any sibling explicitly, so differentiation relies on inference from the word "update."

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 real preconditions: write consent must be granted and confirmed=true must follow an explicit user confirmation, which is actionable gating guidance. However, it never addresses tool selection — nothing tells the agent when to reach for this versus garmin_create_activity or when not to update at all.

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