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

Annotations declare readOnlyHint=false and destructiveHint=false, so the description doesn't need to restate safety. It adds meaningful behavioral context: 'Appears immediately for all collaborators' (real-time shared visibility) and 'Requires a valid editor access token' (authentication requirement). This goes beyond what the structured annotations convey, aiding the agent in setting expectations for side effects.

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?

The description is three sentences, front-loaded with the core action. Every sentence earns its place: action, style variants with examples, use cases, collaboration behavior, and auth requirement. No redundant phrasing or filler.

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?

Given the tool's complexity (nested annotation object with 15 optional properties), the high schema coverage means the description doesn't need to enumerate fields. It covers what the schema cannot: when to use which style, live collaboration visibility, and auth. The description gives a complete enough mental model for an agent to select and invoke the tool, though it doesn't mention the action_explanation parameter or the constraint on id formatting (both already in schema).

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?

The input schema covers 100% of parameters with descriptions, so the baseline is 3. The description adds value by explaining the semantic distinction between stickyNote and textBody styles and linking them to use cases (titles/labels vs. notes/callouts). This helps the agent choose appropriate parameter values, especially for the 'style' field, which is otherwise just an optional enum-like string.

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 description opens with a specific verb+resource: 'Adds a text annotation to a live Trident document.' It clearly distinguishes this from sibling tools like add_node and add_connection by specifying text annotation, and further clarifies scope with two named visual styles. The intended uses (architectural notes, decision records, etc.) make the purpose unambiguous.

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 description provides explicit use-case guidance: 'Ideal for architectural notes, decision records, section labels, or TODO markers.' It also gives context for choosing between the two styles, which serves as a 'when to use this variant' guideline. It doesn't explicitly mention when NOT to use this tool versus update_annotation/delete_annotation, but the phrasing implies annotation creation for live collaborative documents.

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