production.character_redesign_session

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

Adds important context beyond annotations: readOnlyHint=false is explained (apply=true creates candidates, renders, does QA), yet destructiveHint=false is reinforced by stressing that the true apply stays in a separate call. Discloses side effects (renders, deformation QA wiring via rig/stress_poses). Would be a 5 if it stated exactly what apply=true persists versus previews.

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?

Effectively two dense sentences that front-load the mode semantics (apply=false default, no mutation) before expanding apply=true. Every clause carries meaning, though the second sentence is quite packed and could be split for readability.

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 needn't be described, and the description covers the mode logic. But for an 8-parameter orchestration tool with 0% schema coverage, leaving intent/object_name/operation_id/manifest undocumented is a meaningful completeness gap.

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 must carry parameter meaning. It usefully explains apply, step (plan step N), rig and stress_poses in the QA context, but leaves object_name, intent, manifest and operation_id completely unexplained. Half the parameters remain ambiguous.

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 resource ('Guided session') and enumerates the phases it runs (inspect, audit, plan, risk) plus the apply=true cycle contents. It clearly distinguishes its two modes and names the sibling (character_adjust_shape) that performs the real change. The only gap is that it never plainly says 'orchestrator over a redesign workflow' in a single crisp phrase.

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?

Explicitly says apply=false is the default and non-mutating, apply=true runs one cycle of step N, and the actual apply must be a separate character_adjust_shape call. This gives real when-to-use direction against the key alternative. It does not, however, contrast against the many sibling analysis tools (character_redesign_plan, character_create_candidate, etc.) that overlap with its internal phases.

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