Add a margin annotation

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

With no annotations provided, description discloses key behavior of automatic shared card creation on overlapping annotations. Does not mention if annotations are overwritten or other side effects, but provides useful context beyond basic purpose.

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?

Two concise sentences: first states core purpose, second adds constraints and key side effect. No unnecessary words.

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?

Covers main action and important side effect (shared card creation). Lacks description of return value or confirmation, but for a simple mutation tool this is adequate.

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 low (40%). Description adds meaning for 'quote' (short exact quote) and 'author' (enum values), but two parameters (bookId, chunkId) remain 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?

Clear verb 'add' and resource 'annotation' anchored to quoted passage within a chunk. Distinct from sibling tools like list_annotations which only list annotations.

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?

Provides explicit constraint that author must be 'human' or 'claude', and describes automatic card creation if overlapping annotation exists. However, does not explicitly state when to use this tool vs alternatives like append_notes.

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