workspace.create

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

Annotations declare destructiveHint=true, idempotentHint=false, and openWorldHint=false, so safety-critical traits are flagged structurally. The description adds only that an 'optional baseline is copied from configured read roots', but never discloses what the destructive behavior actually destroys or overwrites, nor why re-invocation is non-idempotent. For a destructive, non-idempotent mutation the disclosure is thin.

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 tight sentences with the core action front-loaded and no filler. It is appropriately short, though the second sentence is doing double duty as both disambiguation and behavioral note without fully developing either.

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 described, but the tool is destructive, non-idempotent, takes six largely opaque parameters including nested objects, and the description covers none of that. The one useful detail (baseline copied from configured read roots) is insufficient for an agent to invoke this safely.

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 six parameters, several of which are nested objects (target, project_target) with additionalProperties, plus task_id, revision, baseline_path, and expected_sha256. The description touches only the concept of a baseline, leaving the required 'target' object and the sha256/revision semantics entirely unexplained in both schema and prose.

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 verb+resource: 'Create isolated file workspace.' It also explicitly contrasts itself with a similarly named operation ('This is not native project.create'), which prevents a likely confusion. No contrast is drawn against the actual sibling tools (workspace.import, workflow.start), so it stops short of full sibling differentiation.

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 only routing guidance is a negative disambiguation against 'project.create', a tool not present in the sibling list. There is no statement of when to choose workspace.create over workspace.import, workspace.status, or workflow.start, and no prerequisites or preconditions are given.

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