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

Annotations already declare destructiveRewrite behavior (readOnlyHint=false, destructiveHint=true, openWorldHint=true). The description adds genuine context beyond these: it reuses the 'web write gateway, validation and budgets' (signalling validation/budget enforcement) and requires a participant token for auth. That is useful, but it stops short of stating what gets destroyed or what the return shape is.

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 short sentences with no obvious padding, and the app-only/transport nature is front-loaded. However, the sentences are dense with internal jargon that reduces usable signal per sentence.

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 complex 7-parameter mutation tool with nested objects, no output schema and only partial annotation coverage, the description is far too thin. It omits operation semantics, payload structure, the ID-vs-token distinctions, and any result/error behavior an agent would need.

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?

With 7 parameters and 0% schema description coverage, the description must carry the load, but it only gestures at participant_token and 'saved-plan' (plan). It never explains operation, payload, participant_id, target_participant_id, or target_participant_token, leaving most parameters undocumented in both schema and description.

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 name 'widget_write' and title 'Save from the planner' suggest a write/save operation, but the description calls it an 'App-only transport for explicit interactions with shared web components', which is jargon that does not clearly state a verb+resource. It never says what is being written or saved, so an agent cannot confidently distinguish it from widget_lookup or widget_select_participant.

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?

The only usage hint is 'Requires the selected participant token for saved-plan edits', which implies a prior widget_select_participant step and a saved-plan context, but there is no explicit when-to-use/when-not-to-use guidance or named alternative among the many siblings.

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