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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description does not need to restate safety. It adds useful behavioral context beyond annotations by specifying what the run view contains (per-step timing, ending causes, pauses, drift) and that it requires the user's Rhylthyme account.

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, front-loaded with the primary action and immediately followed by the distinguishing payload. Every clause earns its place; even 'Shows where a plan drifts' adds the practical purpose rather than repeating prior content.

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 simple read-only tool with well-covered schema and strong annotations, the description is largely complete: it names the resource, the displayed information, and the account prerequisite. It does not describe return format, but the absence of an output schema and the 'shows' wording make the behavior understandable enough for correct invocation.

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%, with clear descriptions for run_id ('Run UUID from list_runs') and token ('Access token from the login tool. Omit when the account is connected.'). The description adds no parameter-specific semantics; the baseline of 3 is appropriate because the schema already carries the full parameter burden.

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?

The description uses a specific verb and resource ('Open one recorded run') and immediately clarifies the tool's distinctive content: planned vs actual timing, step outcomes, and pauses. It differentiates from siblings like list_runs (one run, not a list) and load_program (run execution data, not source). This is not a mere restatement of the title.

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?

The description clearly implies when to use the tool: when you need one recorded run's execution detail and plan drift. It does not explicitly name sibling alternatives or exclusion conditions, but 'Open one recorded run' and the content description give clear context for selection.

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