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

With no annotations, the description carries the behavioral burden and largely does: it discloses server-side CSV parsing/staging, that it can invoke ingest_accounts with map_session_id, that fixed-workload args are normalized to auto_build fixed_workload_target, and that modern vs legacy clients get different clarification behavior. It omits what happens to unhandled or ambiguous requests and any auth/side-effect scope, but the disclosed traits are substantial.

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?

It is front-loaded with the use case, but it is a single dense block overloaded with opaque jargon ('HITL-025', 'CLARIFICATION_REQUIRED', 'protocol >= 2026-07-28', 'part_layer/tal_label') that an agent must parse rather than act on directly. Several clauses earn their place; the internal reference codes do not.

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?

An output schema exists, so return values need not be described, but for a 9-parameter orchestrator with zero annotation coverage the description does not explain how the request string maps to the many sibling workflows, nor what the caller should do when the request is under-specified beyond the modern/legacy clarification note.

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% across 9 parameters, so the description must compensate. It explains request, csv_file, accounts_handle, assignments_handle, map_session_id, and ts_handle, plus args keys, but leaves state_facts and guidance_handle entirely unexplained, so a meaningful gap remains.

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 frames 'ezt' as a plain-language orchestrator that carries a goal to the right underlying action, and it distinguishes itself from siblings by telling the agent to prefer granular tools when the step is known. The verb is inherently generic ('orchestrate whatever the request implies'), so the resource is left implicit, but an agent can still tell what class of behavior to expect.

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-to-use ('when the exact granular tool is unclear or when a greedy/file-holding client wants to complete an action in one step') and an explicit when-not with the alternative ('Prefer granular tools directly when you know the step'). That is a complete routing rule.

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