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

Annotations declare readOnlyHint=false and destructiveHint=false, so the description's job is to add behavior beyond that. It does: the prune criterion is connectivity-based and conservative, zones are refilled and the unconnected count compared, and the run takes minutes on a large board, which is exactly the runtime expectation an agent needs. It does not note reversibility or that the board is modified in place, but the annotations plus this context cover most of the burden.

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-loads the core action and its criterion, then the parameter hint, then runtime and follow-ups — no filler, every clause carries information.

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 4-parameter, no-output-schema mutation tool, the description covers what changes (vias removed, zones refilled), how long it takes, and what to run next. It leaves the workers parameter and the return/status flow (running via get_board_job) only partially addressed in the description, but the schema covers wait_s.

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 coverage is 50% (nets and workers are bare in the schema). The description compensates meaningfully for nets by explaining it as a candidate limiter and hinting GND/plane rails are the productive targets; wait_s and design_id are already documented in the schema. workers and the nets ordering priority are still left implicit, keeping this below a 5.

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+resource ('Remove every via the board does not need') with the deciding criterion spelled out (a via stays only if removing it disconnects something). This clearly distinguishes it from siblings like polish_vias and cleanup_board, which do not remove vias under a connectivity test.

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 concrete selection guidance ('nets limits the candidates (GND and the plane rails first)') and a follow-up sequence ('then fill_zones, run_drc and score_board'). It stops short of naming alternatives it competes with (e.g., polish_vias) or stating when not to run it, so it is clear context but not full when/when-not coverage.

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