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

Annotations declare non-readOnly, non-idempotent, non-destructive, and the description usefully goes beyond them: a brand-new execution is created rather than resuming the original, it reuses the original payload, and it restarts from the beginning — which explains why the tool is not idempotent. It does not cover permissions, retention of the original execution, or rate/quota implications. No contradiction with annotations.

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 tight sentences, zero filler; the state qualifier and the new-execution semantics are front-loaded, and the diagnostic warning is appended last where it is most actionable.

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 single-parameter mutation tool with no output schema, the description supplies everything an agent needs: eligibility (terminal states), the resulting behavior, and the prerequisite diagnostic step. Nothing material 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?

Only one parameter exists and schema description coverage is 100%, so the schema already documents execution_id and its source (list_recent_executions). The description adds no parameter-level detail beyond the implicit requirement that the target be in a terminal state, 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?

States a specific verb (retry) and resource (execution) and narrows scope to terminal executions only, listing the qualifying states (failed, cancelled, or timeout). It also explains the mechanics — a new execution is created with the original's payload and runs from the start — which cleanly separates it from sibling retry_data_run, retry_application and from cancel_execution.

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 clear preconditions and routes the agent to a named alternative: 'Read the failure first with get_execution_details'. The caution that retrying without fixing the cause reproduces the failure functions as implicit when-not guidance. It stops short of naming the other retry/cancel siblings or stating explicitly that it must not be used on in-flight executions.

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