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

With no annotations present, the description carries the full burden and does so well: it distinguishes checkpoint continuation (paused, resumes the parked hop) from re-execution (errored, re-runs the failed node), flags the conditional argument requirement, and discloses the editor-permission requirement. These are non-obvious behavioral traits an agent could not infer from the schema.

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, zero filler, and the core action is front-loaded with the per-state behavior clauses following. Every clause carries information the caller needs.

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 tool with no annotations and no output schema, the description covers state-specific behavior, the conditional argument, and permissions. It stops short of describing what the resumed run returns or how partial progress is surfaced, which is a minor gap.

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 runId and maxCostUsd are already documented in the schema, including the conditional requirement for maxCostUsd. The description largely restates this ('requires a new maxCostUsd in the arguments'), adding no format, range, or constraint detail beyond structured data.

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 (resume) plus resource (run), and immediately scopes it to two distinct states (paused, errored) with different semantics. An agent can distinguish this from cancel_run, pause_run, or start_run without opening any 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 clear conditional guidance: a budget_exceeded run requires a new maxCostUsd, and editor access on the run's graph is a prerequisite. It does not explicitly contrast with start_run for non-resumable states, but the state conditions are specific enough to route correctly.

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