manage_publishing_pause

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

Annotations only say destructive/not-idempotent/non-readOnly; the description adds what actually gets destroyed or blocked (scheduled posts held, Post now blocked until an admin resumes), the required permission tier per action (Publisher vs admin), and the seat-limited-brand constraint. It also discloses the non-obvious post-pause semantics: posts whose time passed stay paused, are listed as missed, and never publish on their own. That is substantive context beyond 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?

Front-loaded with the core purpose and the do-not-act-unprompted rule, then organized by action. It is dense and long with heavy parenthetical nesting ("(optional brand_id; leave it out for the whole workspace)"), which costs some scannability, but almost every clause carries operational information.

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 destructive, multi-action, permission-gated tool with no output schema, the description covers permissions per action, the preview/confirm handshake, scope defaults (workspace vs brand), and the missed-post lifecycle. An agent has everything needed to call it safely and correctly without inferring.

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 schema already documents confirm, brand_id, and post_ids per action, so the description's per-parameter notes largely restate it. It does add cross-parameter meaning the schema cannot: confirm belongs to a preview-then-agree workflow, and post_ids must come from a resume's output. Marginal but real value over a fully documented schema.

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?

Opens with a specific verb pair and resource: "Pause or resume publishing for a whole workspace or one brand," and immediately names the sibling to check first (list_publishing_pauses). The three actions (pause, resume, publish_missed) and their scopes are stated explicitly, so an agent can distinguish this from list_publishing_pauses 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?

Gives explicit when-to-use and when-not-to-use guidance: "Only act when the user asks; never pause on your own initiative," plus "check it first with list_publishing_pauses." It also prescribes the exact two-call protocol (preview without confirm, show the user, then confirm=true), leaving no ambiguity about sequencing.

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