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

Annotations declare the destructive/open-world profile, and the description adds substantial context beyond that: unmentioned content is preserved (patch semantics), a bad patch is rejected wholesale with an error naming the path and allowed values, and the home dashboard enforces an undeletable status card and topic cards. These are behavioral traits an agent could not infer from the annotations alone.

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?

Purpose and patch semantics are front-loaded, and nearly every sentence carries non-redundant guidance (defaults, rejection behavior, home-dashboard constraints). It is dense and somewhat run-on in the middle ('A dashboard document is one wall of cards in order...'), which costs a point on readability rather than on wasted content.

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 nested-patch mutation with an output schema and full annotation coverage, the description covers everything an agent needs: id sourcing, patch vs replace semantics, default widget/size behavior, validation failure mode, and dashboard-size rules. Nothing material is left to inference.

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, and the description adds genuine meaning: size 'auto' is derived from the widgets, style overrides card color/icon from tiles.icons, theme.density compact tightens tiles, and widgets may be omitted when upserting a card that names a topic (defaults apply). It does not enumerate every nested enum, hence 4 rather than 5.

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 first sentence names a specific verb and resource ("Changes a dashboard's title or document") and immediately reframes 'document' as a patch rather than a replacement, which distinguishes it from create_dashboard and get_dashboard. It also points the agent at the needed sibling data sources (get_dashboard ids, get_capabilities for widgets/draws, update_topic for scene visuals).

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?

Explicit when-to-use and when-not guidance is present: read get_dashboard first and reuse ids, leave size at auto and style alone unless the user asks, keep at most 8 cards and split other themes onto their own dashboard, and on the home dashboard restyle/resize/reorder instead of removing because removal is reverted. These are concrete conditions and alternatives tied to real states.

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