keystone_apply_patches

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

With no annotations provided, the description carries the full burden. It discloses forward-only behavior (irreversibility), handling of user-modified files (skipped and reported as conflicts), and the current no-op behavior ('Today no patches ship'). This is good behavioral transparency, though it could mention permissions or explicit side effects.

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 concise (three sentences), front-loaded with the core purpose, and every sentence adds useful information (forward-only, conflict handling, current empty state, future path). No redundancy.

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 sufficiently covers the tool's behavior, current status, and future evolution. It mentions the output ('empty applied list') and the patch location ('templates/patches/<version>/'), which is complete for a parameterless tool with an output schema.

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?

The tool has zero parameters, and schema coverage is trivially 100%. The description adds no parameter details, but none are needed. Baseline for 0 params is 4, and no reason to lower.

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 clearly states the tool's function: 'Apply every pending shipped patch to the project harness.' This is a specific verb ('apply') and target resource ('project harness'), and it distinguishes the tool from siblings like keystone_harness_bootstrap by focusing on patch application.

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 description provides clear context: it is used to apply shipped patches, with the caveat that patches are forward-only and user-modified files are skipped and reported as conflicts. It implies the tool is used for incremental updates but does not explicitly name alternatives or state 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.