Summarize comments

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

The description adds behavioral context beyond the annotations: it explicitly states 'Reads every page of comments,' which signals that this operation may be costly or time-consuming. The annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, but the description's note about reading all pages is an additional useful disclosure. No contradictions with annotations exist.

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 with no wasted words. The first sentence front-loads the core purpose and lists the key outputs, and the second adds a single behavioral note. It is tightly written and every phrase contributes value, making it an excellent example of conciseness.

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 summary tool with no output schema, the description covers the key return content (counts by status, participants, open comments, etc.) and the behavior (reads all pages). It does not explicitly mention the format parameter or the output format, but the format parameter with its enum is present in the schema. The annotations handle the read-only safety. Overall, the description provides sufficient context for an agent to invoke it correctly, with minor gaps like not stating the return type directly.

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 50%: the document parameter has a clear description, but format has no description beyond its enum values. The description does not elaborate on either parameter. However, the format enum (markdown/json) is self-explanatory, and the document parameter is already well-documented. Since the coverage is not high (>80%) but also not low (<50%), the baseline is 3, and the description adds no extra parameter meaning, so a 3 is justified.

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 provides an aggregate view of all comments in a Google Doc, listing specific metrics like counts by status, participant activity, and open comment details. It distinguishes itself from siblings like list_comments or get_comment by focusing on summary data rather than raw comment listings, though it does not use an explicit verb like 'get' or 'retrieve'. The resource (comments in a Google Doc) and the nature of the output are clear, so it earns a 4 rather than a 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 implies when to use this tool—when an aggregate summary is needed rather than individual comments—but it does not explicitly mention alternatives or conditions for choosing this over list_comments or get_comment. It says 'Aggregate view' which suggests it's for high-level insights, but there is no direct 'use this when' or 'use list_comments for details' guidance. This is adequate but not explicit, so a 3 is appropriate.

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