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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral facts beyond them: validation semantics, the hash-binding contract, the explicit-authorization prerequisite for the follow-up apply, and the separate schedule permission requirement. It does not cover failure modes (what happens on invalid items or hash mismatch) or batch-size limits.

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 sentences, each load-bearing, with the core action and the key negation front-loaded. It is dense but not padded; the only mild cost is that the first sentence packs five snapshot fields into one clause, which reads as a list rather than prose.

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 explained, and the description does cover the non-mutation guarantee, permission prerequisite, and hash contract. However, for a tool whose parameters are entirely undocumented in the schema, omitting any explanation of the batch item structure and the expectedPreviewHash comparison leaves a real gap an agent must fill by reading the raw JSON schema.

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 three top-level parameters plus a deeply nested items object with six required sub-fields, so the description carries the full burden — and it explains none of them. Terms like 'exact batch' and 'previewHash' gesture at items and expectedPreviewHash, but idempotencyKey, localDateTime, timezone, dstDisambiguation, and approveExactContent are never given meaning, nor is the role of expectedPreviewHash in a re-preview/compare flow.

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 and resource ('Validates an exact batch of saved Posts and returns a snapshot...') and enumerates the snapshot contents: destination, copy, media identity, revision, future time, plus a previewHash. The explicit negation 'This does not approve, schedule, or publish anything' cleanly separates it from schedule_posts and the other preview_* siblings.

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?

Gives a clear when-to-use context: call this to bind current saved content and timing before a separate apply action, which 'requires that exact hash after the user explicitly authorizes the exact future schedule.' That is a strong usage contract. It stops short of naming the apply/schedule sibling explicitly, so the agent must infer which tool consumes the hash.

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