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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuinely new behavior: write permission is required, both credentials and session are removed, the API key survives, and every response must be checked for serviceAnnouncements. It stops short of stating irreversibility or effects on already-issued tokens.

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 action and its safety gate in the first clause, then prerequisites, then the exclusion. The serviceAnnouncements sentence reads as cross-cutting boilerplate rather than tool-specific behavior, but it is short and prescribes a required output step, so it still earns its place.

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 one-parameter destructive tool with no output schema, the description covers the safety gate, permission requirement, deletion scope, and required post-response handling. It leaves open what happens to existing sessions on other clients and whether the deletion is reversible, which an agent facing a destructive action would benefit from knowing.

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 0%, but the single parameter is a const-true boolean that documents itself. The phrase 'only after explicit confirmation' still adds meaning: the flag must reflect user consent, not a default or an inferred intent, which is the key semantic an agent could otherwise get wrong.

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 and resource: delete hosted Garmin credentials and the session. The scope ('credentials and session only') also implicitly distinguishes it from garmin_account_status and garmin_acknowledge_announcement, so an agent can tell what this tool does and does not touch.

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 a clear precondition ('only after explicit confirmation'), a permission prerequisite ('Requires write permission'), and an explicit exclusion — Personal API key revocation happens separately in Garmin, not here. It does not name a sibling tool for the alternative path, which keeps it 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.