get_post_comments

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

With no annotations, the description carries the full burden, and it does add meaningful context: the endpoint path, valid order values (chronological/reverse_chronological), filter semantics, and the 'from' field shape in output. However, it's silent on pagination behavior (after/limit interplay), default ordering behavior, and any rate-limit or error characteristics. The additions are relevant but partial; this is a solid middle-of-the-road effort with no annotations to help.

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?

Four tightly packed lines: a purpose sentence, two parameter docs, and one output-shape note. Every sentence contributes, the parameter docs are formatted as scannable label/value pairs, and there's no fluff or repetition. A half-point deduction for output 'from' note being slightly terse (could clarify id/name visibility rules).

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?

Given an output schema is present, the description doesn't need to enumerate return values — and it wisely documents only the non-obvious output detail ('from'). However, pagination semantics for `after`/`limit` are underexplained for a listing tool, and there's no mention of how `filter=stream` interacts with ordering or limits. Adequate for straightforward calls but leaves an agent guessing on multi-page or streaming scenarios.

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 0%, so the description must compensate — and it does document semantics for the two least obvious params (order and filter). However, after, limit, post_id, and fields receive no described meaning beyond their self-evident names, and the default fields list in the schema (like comment_count, permalink_url) does some implicit work. Meaningful for the ambiguous params, but with 6 total params, substantial room remains.

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 verb+resource: 'List comments on a post' with the endpoint specified as (GET /{post-id}/comments). The description conveys this is a collection-listing operation, distinct from get_comment and get_comment_replies. Loses a point for not explicitly differentiating itself from those siblings, particularly given get_comment_replies overlaps with the 'stream' filter behavior.

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?

No explicit when-to-use guidance or mention of alternatives. The 'filter' param description (toplevel vs stream) implies a decision between flat and nested comment output, but the description never says 'use get_comment_replies for X' or when not to use this tool. The endpoint and param docs emerge from parameter documentation, not usage guidance.

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