workspace_refresh

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

With no annotations, the description carries the full burden and does well: it discloses reloading, rebuilding, restarting clangd, and preserving unchanged cache files. It could mention potential disruption to open sessions, but the core side effects are clearly stated.

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 description is a single dense sentence with no filler. The 'rebuilt' phrasing is slightly awkward, but the sentence conveys multiple key behaviors efficiently.

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?

The description is adequate for a single-action tool but leaves gaps: no usage guidance, no parameter explanation, and no indication of return or failure behavior. Given the simple schema, it is minimally viable rather than complete.

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% and the description does not mention the optional 'reason' parameter. The schema only provides a type and default, so the description adds no semantic value beyond the schema for this parameter.

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 uses specific verbs and objects: 'Reload compile commands and rebuilt PCM/modmap artifacts, restarting clangd'. It clearly identifies the tool's primary action and scope, though it does not explicitly differentiate from sibling tools like workspace_warm.

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 behavior implies use when compile commands or generated artifacts are stale and clangd needs restarting, but there is no explicit guidance on when to prefer this over sibling tools or when not to use it.

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