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

Annotations already establish this is a non-read-only, non-destructive, closed-world write. The description adds real behavioral context beyond them: a new pro widget consumes the plan's widget limit, accounts are capped by the plan, campaigns are Instagram/Pro-only, and review widgets silently filter out hidden and pending reviews. Return shape is also characterized as equivalent to get_widget with a reviews_shown count.

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 purpose, then mode-specific requirements, then post-creation workflow and plan side effect. The prose is dense and somewhat comma-spliced, but each sentence contributes a distinct fact and nothing is padded.

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 six-parameter mutation tool with no output schema, the description covers both usage modes, the prerequisites and their sibling tools, the returned object, the plan-limit side effect, and a post-creation next step. An agent has enough to call it correctly and to interpret the response.

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 100%, so the schema already carries the per-parameter meaning and the kind enum default. The description mostly restates that (first account supplies service/header, remaining accounts add posts, source_ids default to all sources) and adds only marginal linkage between source_ids, the "shown" count in list_review_sources, and reviews_shown.

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 and resource ("Makes a widget") and immediately splits the operation into its two concrete modes, social and review, each with its required inputs. The agent can distinguish this from get_widget, update_widget, preview_widget and copy_widget without opening any 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 a clear workflow: create here, then adjust settings with update_widget, then use get_embed_code to publish. It also names the prerequisite listing tools (list_accounts, list_widget_types, list_campaigns, list_review_sources) that supply valid ids. It stops short of stating when NOT to use this (e.g. duplicating an existing widget via copy_widget), so not a 5.

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