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

Annotations already cover readOnly, idempotent, non-destructive and openWorld, so the bar is lower. The description adds genuinely new behavior: it returns what was found on the drawing plus a stable camera and an applied focus query, and it promises 'Unknown references are never invented' — a useful statement about how bad inputs are handled rather than fabricated. It doesn't say what happens when nothing matches or whether the viewer state changes persistently.

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?

Three tight sentences, front-loaded with the action and immediately followed by return behavior and the one non-obvious parameter format. No filler. Dense but 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?

An output schema exists, so return values need not be explained, and the tool is fairly complex (6 params, nested object, three optional ID variants for single-version vs compare mode). The description never clarifies how board/documentId/versionId relate or when to supply compareBaseVersionId and compareHeadVersionId together, which is the main gap for correct invocation.

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 carry parameter meaning. It does well on the nested focus object — naming refs, nets, layers, change, and explaining 'focus.sheet accepts the sheet name or the KiCad sheet path as read_schematic returns it ("/Connectors/")' with a concrete format example. But it is silent on the top-level board, documentId, versionId, compareBaseVersionId and compareHeadVersionId interplay, which is the harder selection problem for an agent.

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 opens with a specific verb and resource: 'Retarget the open BoardRepo viewer to highlight specific references, nets, layers or a compare change on an exact saved version.' That tells an agent this is a viewer-manipulation tool, not a data fetch. It stops short of naming a sibling (e.g. show_board, get_board_view) to disambiguate which of several view tools to call.

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 phrase 'the open BoardRepo viewer' implies a prerequisite (a viewer/session already exists) and 'on an exact saved version' hints at the versioning requirement. However, it never states when to prefer this over show_board or get_board_view, nor what happens if no viewer is open. Usage selection is left to inference.

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