reevaluate_execution

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the mutation and safety profile is known; the description adds the crucial versioning semantics ('kept as a new version, never overwriting the previous one') and the feature-flag prerequisite, both beyond structured fields. It stops short of describing cost, latency, or when the new version becomes visible, which keeps it at a 4.

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 doing distinct work: action plus non-destructive guarantee, parameter discovery, then prerequisite and alternative. Zero filler and the distinguishing constraint is front-loaded.

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?

With an output schema present and annotations covering safety, the remaining agent needs — prerequisite, ID provenance, task-level alternative, and the non-overwrite guarantee — are all covered. Nothing required to invoke it correctly is missing.

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 baseline is 3, but the description adds provenance for execution_id by naming the two tools that surface it. It says nothing about task_type, whose grouping purpose is left entirely to the schema.

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 ('Force a fresh Evaluation Engine pass over one specific execution') and immediately scopes it to a single execution, which differentiates it from the task-level sibling evaluate_task. An agent can pick between the two without opening either schema.

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 explicit routing: 'to score a whole task use evaluate_task', a prerequisite ('Requires evaluation_engine enabled'), and how to obtain the required execution_id via get_task_evaluations or get_task_result. Both the when and the when-not are present.

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