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

Annotations only give the generic safety profile; the description adds real behavior: default zone extent is the whole board outline, priority orders overlapping fills, clearance_mm/min_thickness_mm override design rules, and thermal=false solid-connects pads. It also discloses remove matching semantics (zone or net names, wildcards) and its keepout exclusion. Missing only return/result shape and failure behavior.

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?

Front-loaded with the core action, then packed detail in compact clauses; every sentence carries information. The semicolon-chained phrasing is dense and takes a second pass to parse, costing a point versus a cleanly broken-out 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 nested-array mutation tool with no output schema, the description covers creation shape, defaults, ordering rules, overrides, and post-steps. It does not say whether added zones merge with or replace existing ones, nor what the response contains, which are the remaining gaps.

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?

With 50% schema coverage, the description usefully explains the semantics of priority, clearance_mm, min_thickness_mm, thermal, and the net/layers/rect/polygon fields — meaning well beyond their bare types. However, name, design_id, and wait_s are left entirely to the schema, so it does not fully compensate for the coverage gap.

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?

Opens with a specific verb pair and resource: 'Add or remove copper zones (pours).' It then scopes the operation (net poured on given copper layers, over rect or polygon, defaulting to the whole board outline), which clearly separates it from add_copper, set_keepouts, and tidy_copper.

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?

Gives explicit workflow ordering — 'Run fill_zones afterwards, then run_drc' — and states a boundary condition ('remove ... never touches keepout areas'), implicitly routing keepout edits to set_keepouts. It does not say when to prefer this over add_copper for simple copper shapes, but the sequencing context is strong.

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