Preview exact Ghost changes

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

Annotations already declare readOnlyHint/idempotentHint, so the safety profile is covered. The description still adds real value: the hard 25-item limit, the fact that results are a stateless site-bound hash, and the returned approval scopes and before-snapshots. It stops short of discussing staleness or failure behavior, so not a 5.

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, zero filler, and the read-only guarantee is front-loaded at the end where it caps the summary cleanly. Every clause adds information an agent can act on.

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 minimal narration, yet the description still names the key payload elements. For a single-parameter preview tool this is nearly complete; only the optimistic-concurrency semantics of target.updated_at are left unmentioned.

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 burden; it compensates partly by conveying the 25-item cap ('up to 25 exact posts or Pages') and hinting at exact-match edits. But it explains nothing about the operation variants (update_fields, replace_body, append/prepend_section, replace_exact_text) or the updated_at concurrency precondition.

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 precise verb and resource ('Read up to 25 exact posts or Pages') and enumerates exactly what comes back (before snapshots, field/Lexical impact, approval scopes, preview hash). This is clearly distinguishable from the write-side sibling apply_change_set 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 closing 'This tool never writes' implies the use case (dry-run before a mutation) but never names apply_change_set or states the when-to-use/when-not condition. An agent must infer the preview-then-apply workflow on its own.

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