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

Annotations already flag destructive/idempotent, and the description adds genuinely non-obvious behavior: omitted fields are preserved (PATCH semantics), null team hours deletes them, empty strings fall back to built-in copy, [] empties questions, the avatar is out of scope here, and no durable mutation receipt exists so the change is unverifiable afterward. That last point especially is behavior no annotation conveys.

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 operation and its scope, then the clearing rules — no filler, and every clause carries information. The semicolon-chained style makes it denser than ideal for scanning, but nothing is redundant.

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?

Output schema exists, so return values needn't be described; the description instead covers the things ambiguity would actually cost an agent — baseline requirement, partial-update behavior, clearing rules, and the absence of an audit trail. For a destructive, nested-object mutation this is complete.

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 baseline is 3, but the description earns above that by explaining the null-vs-empty-string-vs-empty-array clearing semantics that the schema's bare `default: null` fields do not convey. It also frames `data.expected` as a baseline taken from widget_settings_read, which the schema describes only vaguely.

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+resource ('Edits supplied Widget controls') and immediately bounds the scope: changes go live without Agent publication, distinguishing it from publication_publish. It also names the paired read tool, so an agent can tell this apart from widget_settings_read and widget_enable 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?

Explicitly requires the widget_settings_read baseline before editing and directs the agent back to that sibling after a conflict or lost update — clear routing guidance. It stops short of naming when NOT to use it (e.g. channel_settings_edit for non-widget channel config, or widget_enable for turning the widget on), so alternatives are only partially covered.

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