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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, so the safety profile is known. The description adds genuine value by disclosing a response-side behavior: the tool returns serviceAnnouncements from Geekist that must be surfaced distinctly to the user — necessary since there is no output schema. It says nothing about what deletion removes (e.g., scheduled occurrences or linked activities) or how failures are reported.

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 short sentences, front-loaded with the action and its precondition, then the retry prohibition, then response handling. The announcement sentence is somewhat operational boilerplate but is the only source of return-value information, so it 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 two-parameter destructive mutation with no output schema, the description covers the critical decision points: confirmation required, no retry on ambiguity, and a specific response element to relay. Remaining gaps — effect on dependent data and error semantics — are modest given the destructive annotation already sets expectations.

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 50%: workoutId is fully documented in the schema, while 'confirmed' has only type/const and no description. The phrase 'only after explicit confirmation' implicitly explains that 'confirmed' must reflect real user consent, which is a small addition, but the description never mentions either parameter by name or explains their interaction.

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 names a specific verb and resource ('Delete a specific workout') plus a precondition, so the agent knows exactly what the tool does and can tell it apart from garmin_create_workout / garmin_get_workout / garmin_preview_workout by verb. It stops short of explicitly contrasting with the nearest sibling, garmin_delete_activity, leaving that distinction to the resource name.

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?

'Only after explicit confirmation' and 'Do not retry an uncertain deletion' give real when-to-use and when-not-to-use conditions, the latter being important given idempotentHint=false. No alternative tools are named, and there is no guidance on what to do instead when a deletion's outcome is uncertain beyond not retrying.

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