Clear build cache

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the danger is covered. The description adds the useful scope fact that clearing can range from one key to the entire cache, but says nothing about permissions, irreversibility, or how deviceId/deviceName affect the target.

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?

A single tight sentence with the action front-loaded and no filler. It is efficient, though arguably too terse given the parameter and safety burden it must carry.

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 destructive mutation tool with no output schema and 0% parameter coverage, the description is too thin. It omits what 'clear' actually destroys, the effect of omitting key, and the role of the device parameters, leaving an agent unable to invoke it confidently beyond the simplest case.

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% across 3 parameters, so the description carries the burden. It hints at the 'key' parameter ('one content-addressed build-cache key') and implies omission clears everything, but deviceId and deviceName are entirely unexplained in both schema and description.

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 (clear) and resource (build cache) with two clear scopes: a single content-addressed key or the entire cache. It is naturally distinguishable from siblings build_cache_run and build_cache_stats, though it doesn't name them explicitly.

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?

No guidance on when to clear a single key versus the whole cache, no prerequisites, and no reference to alternative tools. The two modes are mentioned but the selection criteria between them is left entirely to inference.

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