analyze_power_budget

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

With no annotations provided, the description carries the full burden and does well: it discloses the kicad-cli read path, the save-first requirement, current-propagation from loads back through regulators/drivers/series parts, the structured 'questions' return on missing data, and the 'unverified_parts' flagging of database values. It stops short of stating whether the tool mutates anything or how heavy/long the run is, but the behavioral picture is substantially richer than a bare 'analyze' verb.

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 text is long but front-loaded (purpose first, then runtime behavior, then remediation workflow, then args) and each block earns its place. The workflow and per-arg guidance are genuinely load-bearing rather than padding, though it could be trimmed slightly and the args section duplicates some schema-documented 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?

For a complex 6-param analysis tool, the description covers the input contract, the runtime preconditions, and the shape of the response keys an agent must act on ('questions', 'unknown_parts', 'unknown_connectors', 'unverified_parts'). Since an output schema exists, detailed return-field documentation is not required, and nothing critical for correct invocation is missing.

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 compensate fully — and it does. Every one of the 6 parameters is explained with meaning the schema cannot convey: the schematic_path accepted extensions and default, external_loads value shapes ({"J2": 2.5} vs {typ_a/max_a/note}) plus the 'pins' restriction for multi-pin connectors, sources defaults, net_voltages purpose for regulator dissipation, and the role of temp_rise_c/copper_oz in width suggestions.

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 opening sentence gives a specific verb and resource ('Estimate how much current every supply net carries, from the schematic, and suggest track widths / net classes'), which clearly differentiates it from siblings like calc_track_width (geometry-only) and set_part_current (writes database values). The scope ('works for any kind of board') and inputs are unambiguous.

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 states the prerequisite ('Reads the saved schematic via kicad-cli (save it first)') and a full remediation workflow when data is missing (answer questions, resolve unknown_parts via datasheets + set_part_current, unknown_connectors via external_loads). It does not explicitly contrast itself with alternatives such as calc_track_width or check_clearance, so an agent must infer when this tool is preferred.

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