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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false), the description discloses real behavioral context: the reset targets pending state and retry happens asynchronously on the next cron tick, not immediately, and ownership/generation are validated server-side. It doesn't say what the caller sees when eligibility checks fail, which is the remaining gap.

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, both information-dense: the action and its async consequence first, the eligibility constraints second. No filler, no restatement of the title.

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 7-param, zero-required mutation tool with no output schema and full annotation coverage, the description supplies the essentials: what state change occurs, when it takes effect, and which runs are ineligible. Caller-visible failure modes are the only notable omission and are minor against the annotated safety profile.

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 71% and the description adds no parameter-level meaning at all — it never says whether run_id or automation_id identifies the target, nor how uid/bearer_token interact with the URL identity described in the schema. With coverage in the middle band the schema carries most of the load, 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?

The description uses a precise verb chain ('Reset ... to pending so Railway retries it') and names the exact resource states it operates on: a succeeded or partial lead or trend-research run with failed delivery. The eligibility sentence ('Manual and generation-failed runs are not deliverable') separates it from run_automation_now and test_automation_delivery without needing to name them.

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?

It gives explicit when-not conditions: manual runs and generation-failed runs are out of scope, and eligibility requires a succeeded/partial run that failed delivery. What's missing is a named alternative — it never says 'use run_automation_now if the generation itself failed' or similar, so the agent must infer the fallback path.

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