Consult Claude Opus read-only

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuinely new behavioral context the annotations cannot convey: the no-edit guarantee for the consultation, and the semantics of the 24-turn minimum as a ceiling rather than a workload, plus the advice to omit max_turns for the reliable default. It stops short of disclosing cost, latency, or session reuse 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 sentences, no filler, with the capability statement front-loaded and the parameter caveat second. Dense and earn-your-place, though the max_turns clause packs two ideas (ceiling semantics plus default advice) into one semicolon splice.

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 read-only safety profile is carried by annotations and the output schema means return values need not be described, so the core job is covered. But with 8 parameters at 0% schema coverage, an agent still has no guidance on mode/effort/focus/context/session_id semantics, which is a real gap for a tool this configurable.

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%, so the description carries the full burden. It explains max_turns well (24-turn minimum is a ceiling, omit to use the default), but mode, task, focus, effort, context, session_id and workspace_path are never addressed, leaving most of the 8 parameters undocumented anywhere.

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 a specific verb set (plan, design, diagnose, review) tied to a named resource (workspace-aware Opus 5 session) and pins the scope with 'without editing files'. That scope contrasts cleanly with the sibling opus_execute, so an agent can separate them without opening either schema.

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 implies usage through the enumerated modes and the 'without editing files' constraint, which hints that opus_execute is the alternative when edits are needed. However, it never states when to pick this tool over opus_execute or opus_status explicitly, and gives no prerequisites or exclusions beyond the read-only framing.

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