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

Annotations already declare destructiveHint=true, so the mutation risk is covered. The description usefully adds the not-started precondition, but it does not disclose what happens to the previous delay value, whether the change is reversible, or any auth/permission requirements.

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?

Two compact sentences plus an endpoint reference, with the core action front-loaded and the precondition immediately after. The endpoint citation is mildly redundant but does not bloat the definition.

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 mutation with no output schema, the description covers the action and its precondition but says nothing about the response or error conditions. Adequate but leaves the agent without confirmation of what a successful reschedule yields.

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%, so both parameters are already documented with format examples ('1h' or ISO-8601). The description adds only the conceptual framing of 'a delayed run' and nothing about accepted delay formats beyond the schema — 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?

States a specific verb and resource ('change when a delayed run will execute') that clearly distinguishes it from sibling mutations like cancel_run or replay_run, and names the underlying endpoint. The scope is narrower and more precise than a generic 'update run'.

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?

Provides an explicit precondition — 'only applies to runs that have not started' — which tells the agent when the tool is valid versus when it will fail. It does not name a fallback tool for runs that have already started, so it falls short of full routing guidance.

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