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

Annotations already flag destructiveHint=true and idempotentHint=false, and the description goes further by explaining exactly what is destroyed: 'Replaces any previous proof reference and completion time for that exercise.' It also states the authority prerequisite and explicitly limits the semantic weight of the record. That is precisely the kind of context the annotations cannot carry.

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, no filler, with the core action front-loaded and the overwrite warning before the caveat. The final clause ('does not prove live customer delivery') is slightly terse but earns its place by preventing over-claiming.

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?

An output schema exists, so return values need no explanation, and the description covers authorization, overwrite behavior, and scope limits for a 3-parameter mutation. What is missing is failure behavior (e.g., what happens if the exercise was never started) and any routing to the sibling tools that handle the surrounding lifecycle.

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 description coverage is 100% and every parameter, including the enum's four values, is documented in the schema. The description adds no per-parameter meaning such as what each exercise name signifies or how partnerId and installationId must relate, so the baseline 3 applies.

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: 'Save completion evidence for a named operational exercise on an existing client installation.' It also bounds the object ('existing client installation') and the four enum exercise names in the schema make the scope concrete. It does not name a sibling, but the action is distinct enough (save evidence) from acknowledge/measure/launch_review that confusion is unlikely.

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 gives one real precondition ('Requires current assigned client authority') and a scope caveat ('does not prove live customer delivery'), which tells the agent what this record is not for. However, it never points to an alternative tool for the adjacent jobs in this family (acknowledge, measure, approve_handoff), so the agent must infer the routing itself.

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