propose_add_comment

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

With no annotations, the description must carry the full behavioral burden. It discloses that DOCX creates a real Word comment, Markdown only stores in-session until process exit, and the tool result explicitly states the limitation. It also mentions the quote constraint. This is transparent, though it doesn't clarify whether 'stage' means the change is not immediately applied (e.g., requiring apply_changes) or cover all 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 well-structured: a clear purpose statement followed by format-specific details and a constraint. It is concise and every sentence provides value, though it could be slightly more compact by merging some lines. Overall, it's efficient and front-loaded.

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?

The description explains format differences and a constraint, but it doesn't explain what 'stage' means in the workflow (e.g., whether it requires apply_changes), nor does it document most parameters. With 8 parameters, an output schema, and no annotations, the description is insufficient for an agent to correctly fill all required fields without additional context.

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%, so the description must compensate for the 8 undocumented parameters. It only explains the constraint on quote (must appear inside the anchor element) and implies the role of anchor_id. It does not explain start, end, doc_hash, author, or path, leaving most parameters ambiguous. This is a significant gap for a tool with this many parameters.

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 clearly states that the tool stages adding a comment anchored to an element, and it distinguishes behavior across DOCX (real Word comment) and Markdown (session-only). It mentions get_comments as a sibling for surfacing comments, which provides some differentiation. However, it doesn't explicitly contrast with other propose_* tools like propose_insert_block, so it's not a perfect 5.

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 gives format-specific guidance (DOCX vs Markdown) and notes the Markdown limitation, which helps the agent decide when to use the tool. It also hints that get_comments is the way to view Markdown comments. However, it doesn't explicitly state when not to use this tool or provide alternatives for different operations, leaving some inference to the agent.

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