wait_exam_browser_save

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

With no annotations present, the description carries the full load and does well: it discloses randomized 2-5 second timing, states the tool is non-mutating (no click, no submit), and imposes an ordering constraint (recheck before proceeding). It omits any statement about permissions, failure modes, or what the tool itself returns.

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 short sentences, front-loaded with the action and followed by the key negative constraints. Some fragmentary phrasing ("No final submission.") duplicates the earlier no-submit statement, costing a little tightness.

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, and the behavioral side is well covered for a wait/authorize step. The gap is the two opaque required IDs and the undefined concept of "authorizing" a draft save, which an agent needs in order to call this correctly in sequence.

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 must explain `run_id` and `plan_id` and does not — neither identifier is mentioned. Only an oblique reference to "the plan's Next/Preview control" hints at what plan_id denotes, leaving an agent to guess how these IDs relate to the exam session.

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 states a concrete action: pause 2-5 seconds after a visible selection and authorize a draft save. However, "authorize draft save" is internal jargon whose effect is not explained, and the description never distinguishes this step from nearby siblings such as `confirm_exam_browser_draft` or `save_owned_exam_answer`, which an agent could easily confuse it with.

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 clear preconditions (after visible selection) and explicit boundaries (does not click or submit; no final submission), plus the required follow-up: the controller must recheck the same question and selection before clicking Next/Preview. It stops short of naming which sibling tool performs that click, so it is a strong 4 rather than a 5.

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