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 known, but the description adds real value beyond them: the schedule is stopped, run history becomes unreachable, and the call may return needs_confirmation. It stops short of stating auth/permission requirements or whether deletion is reversible.

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, each carrying distinct information (what is deleted, what happens to history, what a confirmation response implies), with the primary action front-loaded. No filler.

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 3-parameter destructive tool with no output schema, the description covers the salient outcomes an agent needs: the eval is gone, its schedule stops, history is orphaned, and a confirmation round-trip may be required. Only the permission/auth prerequisites are absent.

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 100%, so the baseline is 3; the description earns above that by explaining the needs_confirmation/approvalId retry cycle, which gives the approvalId parameter meaning the schema alone only partially conveys.

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 ('Deletes an eval') and immediately names the collateral effect ('stops its schedule'). It reads clearly against caliper_evals_update/run/get, though it does not explicitly differentiate itself from the closer sibling caliper_evals_runs_cancel.

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?

There is no when-to-use or when-not-to-use guidance, no statement of prerequisites, and no pointer to alternatives (e.g., cancel a run vs. delete the eval). The only usage-adjacent signal is the approval flow implied by the closing sentence.

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