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

Annotations already establish a safe read (readOnlyHint, idempotentHint, non-destructive, openWorld), and the description adds genuinely new behavioral facts: page has no meaning in directory mode, 40 records per page, a list match is not personal eligibility, unknown projects error while empty known lists return no_data, and output is English natural-language text with sources and conditions preserved.

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 dense sentences with no filler, and the mode split is front-loaded so an agent immediately knows which branch applies. It is on the packed side, but each clause carries operational meaning rather than restating the name.

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?

With no output schema, the description carries the return-shape burden and does so: pagination size, English text output, preserved sources/conditions, and the empty-vs-error distinction. Combined with the mode split and the parameter caveats, an agent has everything needed to call it correctly.

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 low (~40%), so the description must compensate, and it does for the two hardest parameters: it explains that page is meaningless in directory mode, and that program must be an exact previously-returned API identity rather than a user-supplied pathway name. It does not add anything for visaSubclass beyond the conditional that pairs it with program.

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 names two specific verbs and resources: discovering a state/visaSubclass/program directory, and reading one official or national baseline occupation list. The dual-mode framing makes the tool's job unambiguous, though it never names the nearby siblings (get_state_nomination, get_state_nomination_detail) to sharpen the boundary.

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 an explicit conditional: use without program for directory discovery, and with program + visaSubclass to verify identity and read one list. It also states the error semantics (unknown projects are errors, empty known lists are no_data). What is missing is any reference to the sibling tools it should be chosen over.

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