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

Annotations already declare idempotent/open-world/non-destructive, and the description adds real behavioral context beyond them: staged execution gated on approval, dry_run stores nothing, retry semantics keyed on the same plan plus same key, and an account-level beta gate. That is exactly the kind of operational disclosure annotations cannot carry.

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?

Four sentences, each doing distinct work: what it does, what comes back, what gates execution, then the dry_run and idempotency behaviors. The execution gate is front-loaded, so the most decision-relevant fact arrives first.

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 6-parameter mutation tool with no output schema, the description covers the return contents, the approval gate, the beta prerequisite, and the two most subtle parameters. It is silent on failure behavior — notably what happens when the estimate exceeds max_credits — and never mentions webhook_url, leaving the agent dependent on the schema alone for those.

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 100%, so the baseline is 3; the description earns one above it by framing max_credits as a hard ceiling against a single summed estimate and by clarifying the idempotency condition (same key *and* same plan). It does not explain step dependencies or for_each semantics, leaving those entirely to the nested item 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?

"Submit a plan of scrape and search steps... with a required max_credits budget" gives a specific verb (submit) plus resource (run plan) and immediately states the return payload (run id, state, summed estimate). It also explicitly distinguishes itself from the sibling alterlab_run_approve, which is the tool that actually triggers 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?

The when-to-use context is explicit: nothing executes until alterlab_run_approve, dry_run is the validate-only path, and an idempotency_key replays the original run. It also states a prerequisite (the agent-runs beta must be enabled). The gap is that other plausible alternatives in the sibling set — alterlab_estimate_cost, alterlab_batch, alterlab_workflow_run — are never contrasted, so an agent choosing between plan-based runs and batch/workflow tooling gets no routing help.

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