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

Annotations already indicate non-read-only but idempotent and not destructive. The description adds value by disclosing the rate-limited nature of the reply, the preservation of anchor/status, and the comment access requirement. It does not elaborate on the rate-limit behavior itself, but the extra context is meaningful beyond 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 two sentences, front-loaded with the core action and constraints, followed by concise sibling guidance. No wasted 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?

With 4 parameters, output schema, and annotations covering idempotency, the description provides enough for an agent to decide invocation. It covers purpose, access, and alternatives. The rate-limit ambiguity is a minor gap, but the presence of an output schema and good annotations keep it mostly complete.

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 100%, and each parameter has descriptive text. The tool description does not add meaning beyond the schema, but the schema already clearly explains body, threadId, documentId, and idempotencyKey. Baseline of 3 is appropriate.

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 tool's primary action: 'Append a rate-limited reply to an existing review thread without changing its anchor or status.' This specifically names the verb (append), resource (review thread), and scopes (rate-limited, no anchor/status change). It also distinguishes from siblings by naming add_comment and set_thread_status as alternatives.

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 explicitly says when to use this tool vs alternatives: 'Use add_comment to create a new thread or set_thread_status to resolve or reopen one.' It also states the prerequisite of needing comment access, providing clear context for invocation.

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