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

Annotations already declare readOnlyHint and openWorldHint, so the bar is lower, yet the description adds real value: newest-first ordering, replies included with parentId linkage, exclusion of paid-only comments, and a cost of 1 credit. That is meaningful operational context beyond the structured fields.

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?

Three short clauses, front-loaded with the resource and its ordering, then the coverage caveat and cost. Minimal waste, though the opening 'Post comments' fragment is slightly misleading and could be tightened into a single verb phrase.

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 no output schema, the description carries return-shape duty and does so adequately: ordering, reply nesting via parentId, and what is excluded. Missing only pagination/limit behavior and any explanation of cache_max_age, but an agent can call this correctly.

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 50%: `id` is well documented in the schema, but `cache_max_age` is undocumented in both schema and description. The description mentions parentId, which is a response field rather than a parameter, so it does not compensate for the coverage gap; baseline 3 fits.

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 lead 'Post comments' is ambiguous on its own (reads like a write verb), but the next clause disambiguates: 'Every public comment on a Substack post, replies included, newest first' — a specific resource with scope. It is clearly a read of comments tied to a post, distinct from substack_post/substack_posts, though it never names those siblings 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?

Usage is only implied: an agent infers it should call this when it has a post id and wants the comment thread, and the 'paid-subscriber comments not available' note signals a coverage boundary. There is no explicit when-to-use statement and no routing to alternatives such as substack_post or substack_posts to obtain the id.

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