publish_comment

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

With no annotations provided (no readOnlyHint, destructiveHint, etc.), the description must carry the full burden. It tells us it's a POST (mutation) of a comment. However, it doesn't disclose expectations like authentication requirements, visibility settings, or what a successful response contains (though an output schema exists). The behavioral trait of 'creates a comment' is clear, but other important context is left out, so a 3 is the fair baseline since the output schema exists.

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 a single sentence, concise, and front-loaded with the purpose. It includes the useful endpoint reference that adds value without bloat. Every word earns its place.

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 simple mutation tool with only 2 self-explanatory parameters and an output schema present, the description is quite complete. It clearly defines the action, the resource, and the endpoint. The only gap is the lack of explicit behavioral caveats (e.g., requiring authorization) and being only one of many similar-looking tools, but given the simplicity, the state is adequate.

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 schema has 2 parameters, both required, but 0% schema description coverage. The description doesn't elaborate on what 'message' or 'post_id' mean beyond their trivial names. However, 'post_id' is self-explanatory, and 'message' means the text of the comment. It adds minimal value beyond the schema, but the schema already provides enough via names. The lack of further documentation on format or constraints (e.g., length limits) leaves it at 3.

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 does a great job: 'Post a new top-level comment on a post' clearly specifies the verb (post), the resource (a comment), and the scope (top-level, on a post). It even embeds the HTTP endpoint, which clearly distinguishes it from sibling tools like 'reply_to_comment' (which handles replies) and 'publish_page_post' (which posts the page's own post). This removes all ambiguity about what it does.

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?

While the description doesn't explicitly say 'use this instead of reply_to_comment when you want a top-level comment', the term 'top-level' does imply the usage context, contrasting it with 'reply_to_comment' which is for nested replies. The portal-level clarity is good, but it doesn't explicitly mention when not to use it or reference any specific alternative by name, so there is a small gap in proactive routing.

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