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

The description adds behavioral context beyond the annotations: it mentions bearer authentication, idempotent retries via request_key, and that the result is a 'complete private job and checked CSV.' It does not contradict the annotations, which are both false, and provides useful operational expectations.

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 cover the core action, output, authentication, and retry behavior with no filler. The main purpose is front-loaded, and every sentence contributes distinct information.

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 tool with three required parameters and an output schema, the description covers the essential operational context: what it normalizes, what it returns, how to authenticate, and how to handle retries. It could be more complete by pointing to get_job for result retrieval or naming the bounded size limit explicitly, but the schema already carries the size constraints.

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 67%, with csv_text and request_key already described in the input schema. The description adds only light semantic reinforcement: 'explicit column rules' maps to the schema object, and 'Reuse request_key on retries' adds idempotency meaning. The schema parameter itself has no top-level description, but its nested column properties are largely self-documenting.

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 opens with a specific verb and resource: 'Normalize bounded CSV using explicit column rules.' This clearly states the tool's function and scope, and the returned artifacts ('complete private job and checked CSV') reinforce what it produces. It does not explicitly name sibling tools or contrast with them, so it stops short of full 5-level differentiation.

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 first sentence implies the tool is for normalizing bounded CSV data, and the retry guidance ('Reuse request_key on retries') gives operational context. However, there is no explicit statement of when to choose submit_csv over sibling tools such as submit_audit, nor any exclusions or alternative routing.

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