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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavior beyond that: results are owner-scoped and free, pagination must continue until next_cursor is null, links require authentication, and a returned link does not guarantee results are ready. It does not address rate limits or what happens on an unknown/expired job_id.

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?

The content is dense and largely load-bearing, but the opening is a cryptic noun-phrase fragment rather than a front-loaded statement of purpose, and the later sentences chain several distinct ideas (UI link, results_tool routing, auth caveat) without clear structure.

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 fields like next_cursor, job_ui_url and results_tool_arguments need not be explained, and annotations cover safety. However, for a three-parameter tool with zero schema coverage, the description leaves job_id and limit under-specified and does not state what a read of an incomplete job returns.

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%, so the description carries the full burden, and it only partially delivers. It explains the cursor concept ("follow next_cursor until null") but says nothing about job_id's expected format or origin, and nothing about the limit parameter's meaning or interaction with pagination.

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 the fragment "Free, owner-scoped stored results," which implies retrieval of results for a previously submitted job but never states a clear verb+resource pairing. The mention of "never re-submit a completed job" and "results_tool" hints at the relationship to vri_submit_job, but an agent must infer that this tool reads results by job_id rather than being told directly.

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 concrete operating guidance: follow next_cursor until null, do not re-submit a completed job, and use results_tool with results_tool_arguments to read stored results. It stops short of explicitly naming sibling tools like vri_submit_job or vri_operation_status as alternatives, but the sequencing guidance is clear enough to drive correct usage.

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