Apply

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

Annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the agent knows this mutates without being flagged destructive. The description adds no behavioral context beyond that — nothing about what artifacts are written, whether changes are reversible, what confirm actually triggers, or any permission requirement.

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?

Two short sentences with no filler, which is good, but the front-loaded content is spent on enumerating three modes rather than on what this specific tool does. Brevity here costs clarity rather than buying it.

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?

This is a mutating tool with no annotation-based explanation of effects and no statement of what apply produces or alters. The output schema covers return values, but the agent still lacks the core 'what will this change' disclosure needed before invoking a non-idempotent write.

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 100%, so confirm, manifest, workspace, and repository are each documented in the schema itself; baseline 3 applies. The description adds no parameter-level meaning, syntax, or defaults beyond what the schema already provides.

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?

Names the verb (apply) and the resource family (rm_docs_readiness artifacts), but the phrase 'Preview/apply/verify artifacts' describes three separate sibling tools rather than this one, blurring rather than sharpening its identity. The parenthetical '(rm_docs_readiness)' helps only weakly, since rm_docs_readiness_preview and rm_docs_readiness_verify are immediately adjacent siblings.

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?

'after per-repository readiness setup' implies a sequencing prerequisite and the schema text implies confirm is required for apply, but the description never states when to choose this tool over rm_docs_readiness_preview or rm_docs_readiness_verify. Usage is inferable but not spelled out.

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