avl.sweep

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

With all annotations false (no read-only, idempotent, or destructive hints), the description carries the full burden and provides substantial detail: it resets rates and controls, preserves previous tables when outputs is None, retains totals, writes summary.csv, and returns partial results with isError=true on any unsuccessful case. This goes well beyond a minimal disclosure, though it leaves some terms like 'budget' and 'shared AVL processes' somewhat vague.

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 description is compact and front-loaded with the core action in the first sentence. Each subsequent sentence adds distinct behavioral or routing information without redundancy. It could arguably be slightly longer to explain key parameters, but as written it is efficiently structured.

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?

The tool has 8 parameters, no output schema, and no annotations, so the description must provide substantial context. It explains the major behaviors (result ordering, rate reset, output selection, summary.csv, partial results) but leaves a gap around stop_on_error and timeout semantics, which are essential for an agent to invoke the tool correctly under failure conditions. The 'budget' and 'shared AVL processes' concepts are also under-specified.

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 the parameters, but it only touches on a few: conditions (via count and grouping), controls (reset), and outputs (selection and preservation). Critically, it omits stop_on_error, which has a direct relationship with the stated partial-results behavior, and ignores timeout_seconds, references, length_unit, and case_name. This is insufficient for an 8-parameter tool with no schema descriptions.

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 specific verb ('Run') with a clear resource ('conditions in shared AVL processes'), a scope (1-10000 conditions), and a structural detail (grouped by Mach, within one budget). It also distinguishes the tool from a sibling by pointing to 'submit' for long jobs, making the purpose unmistakable.

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 description gives a clear usage boundary: 'For long jobs use submit' explicitly routes to an alternative when the job exceeds the sweep's intended scope. However, it does not explain when to use 'avl.sweep' versus 'avl.run' or other siblings, leaving some inference to the agent.

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