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

Adds meaningful behavior beyond the annotations: backend status may sync at most once per 5 seconds per attempt, and it never spends coins or starts jobs. Since annotations already cover read-only, idempotent, and non-destructive behavior, this extra disclosure is strong.

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 sentences, front-loaded with the primary lookup/recovery modes and then the important side-effect caveat. No wasted text.

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?

Covers input modes and side effects, but with no output schema the description does not explain what status or recovery data is returned, nor error behavior for missing IDs. Adequate but with clear gaps for a retrieval tool.

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 0%, but the description explains the roles of attempt_id and project_id/request_id and links them to the two supported lookup modes. It does not add format details, but it meaningfully compensates for the sparse 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 specific verbs (check/recover) and resources (execution attempt/multi-node workflow), and the contrast with starting jobs or spending coins differentiates it from execution-starting siblings such as start_execution and prepare_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?

Explains the two valid calling modes: attempt_id for an execution attempt or project_id plus request_id for workflow recovery. It does not name an alternative sibling or state when not to use it, so it stops short of explicit when/when-not guidance.

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