sweep_connection_capacities

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

Annotations already declare destructive=false, idempotent=true, openWorld=false, so the safety profile is covered. The description adds genuinely useful behavior: evaluation happens natively server-side in Python with the bound `1 <= steps <= 20`, and it returns a compact inflection table. However it omits cost/latency (each step appears to be a power-flow study) and how `halt_on_violation` changes the run, leaving meaningful behavioral gaps for a heavy operation.

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?

Two sentences, front-loaded with the action and then the rationale for server-side execution. No filler, though the line break mid-sentence and the backtick bound make it slightly less tight than it could be.

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 no explanation, but for an 11-parameter, computationally heavy sweep tool with 0% schema coverage, the definition is thin. It gives no guidance on how the sweep relates to tier1/tier2 screening, no sense of runtime cost, and no clarification of the many numeric/enum knobs an agent must set.

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% across 11 parameters, so the description must compensate and largely doesn't: it only clarifies `steps` (the 1-20 bound). The sweep range (start_kw/end_kw), asset_type, network_id, bess_power_kw, inverter_mode, halt_on_violation, operating_load_factor and feeder_background_scale are left entirely to bare titles and enums.

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?

States a specific verb and resource: 'Execute a server-side N-point hosting-capacity sweep' with the goal of locating 'the exact constraint inflection point'. That is clearly distinct from list_networks or inspect_connection_point, but the description never contrasts itself with run_tier1_screen or run_tier2_ac_study, which are the real alternatives for capacity studies.

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?

'Shields the LLM context window from N sequential tool round-trips' implies the usage pattern (prefer this over looping a single-capacity call N times), but the competing tools are never named and there is no when-not guidance, e.g. when a full tier2 AC study is still required.

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