editor_preview_edit

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context — that the edit is restricted to an allowlist and gated by an expected old value — but omits the outcome when expectedValue does not match, which is the key behavior for a preview tool.

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?

Three short sentences, front-loaded with the core action and the critical 'No world change' guarantee, followed by the minimal type note. No filler, though the type sentence could have been spent on more useful parameter meaning.

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 tool whose entire value is a preview, the description never says what the preview returns (diff, validity flag, resulting value). With no output schema and no annotations covering returns, that is a real gap, though the mutation-safety side is adequately covered.

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 only clarifies that ep_strName is string and ep_bSphere is boolean — largely redundant with the schema's enum/anyOf — and leaves contextId and the distinction between expectedValue and newValue unexplained beyond the phrase 'expected old value'.

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 (preview) plus the resource (an allowlisted property change on the captured selection) and scope (allowlisted fields, no world change). It implicitly contrasts with editor_apply_edit via 'No world change', but never names that sibling, so differentiation is inferred rather than explicit.

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 'preview / no world change' framing implies a dry-run use case before applying, and 'with an expected old value' hints at optimistic concurrency, but there is no explicit when-to-use statement, no exclusion of editor_apply_edit, and no statement of what to do on a value mismatch.

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