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

With no annotations provided, the description carries the full burden. It discloses key behaviors: the server automatically locates quoted_text, omission attaches to the whole document, and offsets can be explicitly provided. It does not cover error cases or permissions but offers meaningful behavioral context beyond a simple statement of 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?

Three sentences, front-loaded with the core purpose, followed by concise usage details. Every sentence provides useful information with no fluff.

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 moderate complexity (5 params, no annotations, no output schema), the description covers the main usage modes (quoted_text, whole document, offsets). It doesn't mention return values or error behavior, but the core invocation semantics are well explained, making it sufficiently complete for an agent to select and use correctly.

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 coverage is 100%, so baseline is 3. The description adds value by explaining the relationship between quoted_text and start_offset/end_offset, and that quoted_text is optional (can be omitted for whole-document annotation). This goes beyond the individual parameter descriptions.

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 starts with 'Add an annotation (comment) to a document,' which is a specific verb ('Add') and resource ('annotation to a document'). It clearly distinguishes from sibling tools like create_document and list_annotations, as it is the only tool for creating 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?

The description provides clear usage guidance: pass quoted_text to annotate a specific passage, omit it to attach to the whole document, or use start_offset/end_offset explicitly. It doesn't explicitly compare to alternatives like list_annotations, but the context is clear and actionable.

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