review_comment

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

With no annotations, the description carries the full behavioral burden. It discloses the anchoring rule (empty quote means start of file) but omits critical context for a mutation tool: whether a review session must first be opened via review_open, whether the file must be open, what happens when the quote isn't found, and whether the call is idempotent or returns a thread identifier.

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 tight sentences, front-loaded with the action and the anchoring mechanism. Every clause carries information; no filler or restatement of the tool name.

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 six-parameter mutation tool with no annotations and no output schema, the description covers the core mechanic but leaves the session prerequisites, failure modes, and return value unaddressed. An agent could invoke it but might do so outside a valid review session.

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 high at 83%, so the schema already documents file, kind, root, quote, and occurrence — baseline is 3. The description does add genuine meaning about quote (empty value anchors to file start), but says nothing about kind (note vs question) or occurrence disambiguation beyond what the schema states.

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 specific verb+resource: "Start a new comment thread" anchored on a quote from a file. The word "new" implicitly distinguishes it from review_reply and review_threads, though no sibling is named explicitly.

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?

It gives purpose-level guidance ("point the user at something: a doubt, a fact to check, a suggestion"), which is real context for when to use it. But it never mentions alternatives (e.g. review_reply for responding in an existing thread) or when not to use it, leaving the routing decision to inference.

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