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

Annotations only declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false); the description goes far beyond that by disclosing the required `content:write` scope, the non-committing nature of the first call, the refusal-by-name behaviour for unsupported fields, and the summary + confirm_token response shape. This is exactly the kind of mutating, two-phase confirmation protocol an agent cannot infer from structured fields, and nothing here conflicts with the annotations.

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 action and then the protocol, with no filler. The telegraphic 'Two calls. The first changes nothing:' style efficiently signals the ordering constraint before the explanatory clause.

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 two-phase mutating tool with no output schema, the description covers the confirmation flow and authorization scope well. However, the schema accepts arbitrary additional properties and the description never says which fields a post actually takes, only that unrecognised ones are rejected by name — a real gap an agent would hit immediately on the first call.

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 coverage is 100% and the single parameter is already described as first-call-omitted / second-call-supplied, so the baseline is 3. The description earns an extra point by framing that parameter inside the whole two-call workflow and tying it to the token returned by the first call, which makes its role clearer than the schema field alone.

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 opens with a specific verb and resource ('Create a post') and spends its remaining words on the mechanics of the create operation, so the agent knows exactly what action produces a new post. It does not explicitly distinguish itself from near-siblings like update_post or restore_post, but the create-vs-modify split is unambiguous from the wording alone.

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?

It gives clear operational guidance for the unusual part of the tool: the first call is a no-op validation, the summarised result must be shown to the person, and the second call repeats identical arguments plus confirm_token. It stops short of stating when this tool should be chosen over update_post or when a post should be created rather than left as a draft, so exclusions are absent.

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