Place App Widget

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

Annotations declare readOnlyHint=false and destructiveHint=false. The description adds genuine value: it discloses the activation prerequisite and the rendering-note behavior of visual positioning. It warns the agent to read the returned rendering note, which is useful context not present in annotations. It doesn't discuss state changes or side effects explicitly, but the critical caveats are covered.

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 sentences, all earning their place. Front-loads the core action, then immediately follows with the critical prerequisite/error handling, then the behavioral caveat about rendering. Zero filler, no repetition of schema 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?

A mutation tool with nested objects (position, config), 7 parameters, and no output schema. The description covers the two most operationally critical behaviors (activation prerequisite and renderRole-based positioning). It could note what the return value represents beyond a 'rendering note,' but given the richness of the annotations and the specific caveats provided, it's reasonably complete for an agent selecting and invoking this tool.

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 0% with 7 parameters, so the description must compensate. It explains the semantic of position (index vs renderRole tier, not necessarily top of page) and mentions config implicitly via widget placement. However, it doesn't clarify what portalRef/pageRef/appKey/widgetKey refer to or how dryRun behaves, leaving some parameters ambiguous despite the good positioning context.

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?

Clear specific verb+resource: 'Place an app widget on a page.' Distinguishes from siblings by naming the exact action and objects involved. Differentiates from related tools like kilango_add_content_block, kilango_update_widget, kilango_move_block, and kilango_reorder_blocks because it specifically addresses placing a widget.

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 states a key prerequisite: 'The app must be installed AND activated in the portal first' and names the specific error (app_not_activated_in_portal) along with the fixing call. Also provides behavioral context about how visual position works ('index 0 is not necessarily top of page'), guiding the agent on interpretation.

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