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

Annotations only indicate readOnlyHint=false and destructiveHint=false. The description goes further by disclosing that it returns the created comment, that ambiguous or missing quoted passages produce a response with candidate passages, and that anchoring within an existing thread creates a reply. This adds meaningful behavioral context beyond the annotations.

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 focused sentences with no filler. The core action is front-loaded, followed by return behavior, error/ambiguity handling, and thread semantics. Every sentence contributes useful information.

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 moderately complex tool, the description covers the main action, return value, failure mode, and thread behavior. The schema fully documents parameters, the output schema exists, and annotations cover safety hints, so nothing essential is missing for an agent to invoke the tool 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?

The input schema already covers all parameters with 100% description coverage, so the baseline is 3. The description adds some context about quoted_text being anchored in the review markdown and ambiguity handling, but it does not materially improve understanding of the parameters beyond what the schema already provides.

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 the action ('Adds a comment'), the resource ('the document under review'), and the anchoring mechanism ('quoted passage of the review markdown'). It also distinguishes itself by noting that anchoring within an existing thread makes the comment a reply, which separates it from the sibling reply_to_comment tool.

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 useful context about when the tool is appropriate—adding anchored comments and handling ambiguous quotes—and notes reply behavior for existing threads. However, it does not explicitly tell an agent when to choose add_comment over the sibling reply_to_comment, nor does it state any exclusion criteria or alternatives.

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