rig.rigify_install

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

Annotations already declare destructiveHint=true, readOnlyHint=false, idempotentHint=false, so the description doesn't need to restate those. It adds useful behavioral context: the gated approval flow, that a client cannot approve its own request, and that it retries the same request id after approval. However, it doesn't explain what destructive side effects occur (e.g., modifying Blender preferences, installing add-on files) or what happens on failure. The added context is meaningful but incomplete.

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 short and front-loads the command identity, but it spends its limited space on risk/maturity labels and approval mechanics rather than on what the tool does. It is not bloated, but it is not well-structured for an agent: the most important missing piece (the action) is absent.

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?

For a destructive, gated, non-idempotent tool with 6 parameters and an output schema, the description is incomplete. It covers the approval flow but omits the core action, the meaning of key parameters, and the nature of the destructive change. The output schema exists but the description doesn't say what the tool returns or how to interpret success. An agent would struggle to decide when to call this and what to pass.

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 50%, and the description adds no parameter-level meaning. The description doesn't explain allowDownload, savePreferences, _expectedSceneRevision, or how they affect the install. The schema documents only _requestId and _authorization; the other four parameters are bare names. With half the parameters undocumented and zero description compensation, the agent cannot infer what values to pass.

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 identifies the command name and risk/maturity level but never states what the tool actually does. 'rig.rigify_install' implies installing Rigify, but the description doesn't say 'installs the Rigify add-on' or describe the effect. It is closer to a tautology than a functional explanation, and it doesn't distinguish it from siblings like blender_rig_rigify_generate or blender_rig_bind.

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 gives operational context (requires local user approval, retries same request id) but no guidance on when to use this tool versus alternatives. It doesn't say 'use this before rigify_generate' or 'use this when Rigify is not yet installed.' The approval flow is a usage constraint, not a when-to-use guideline.

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