Let Claude Opus modify a workspace

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered structurally. The description adds useful context – direct write access, a 'trusted workspace manifest' being returned, and the rationale for the 64-turn minimum (avoiding early truncation) – but omits permissions, reversibility, and rate/limit behavior.

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 dense sentences with the primary action front-loaded and the constraint rationale second. No filler, though the second sentence's turn-minimum note is a fairly narrow detail to spend the tail on.

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 manifest mention is a bonus. Still, for a destructive 8-param write tool with zero schema descriptions, key semantics (workspace_path meaning, session_id reuse, acceptance criteria behavior) are absent.

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 8 parameters, so most fields (task, context, effort, workspace_path, session_id, acceptance_criteria) are undocumented. The description only partially compensates by matching the mode values and referencing the 64-turn minimum for max_turns.

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 states a specific verb+resource: delegating bounded coding tasks to 'Opus 5 with direct write access'. The phrase 'direct write access' implicitly distinguishes it from a read-only consult sibling, but no sibling is named outright.

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?

It enumerates the task classes it handles (implementation, fixes, refactoring, tests, documentation), which maps to the mode enum and implies usage. However, it never states when to prefer this over opus_consult or opus_status, nor any exclusions or prerequisites.

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