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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds two genuinely useful facts – the 1-credit cost and the non-obvious dependency of comment_id on the parent media – but says nothing about pagination behavior beyond what the cursor param implies.

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 sentences, front-loaded with what the tool returns, then the mechanics. The first sentence is a near-verbatim restatement of the title, which is the only waste.

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 does enough: it characterizes the result as a full reply thread, points at the cursor for pagination, and flags cost. A brief note on the response shape or rate/credit semantics would complete it.

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?

Coverage is 80%, so the baseline is 3. The comment_id sourcing text largely restates the schema's own parameter description, and cache_max_age remains undocumented in both places; the one real addition is the rationale for requiring url.

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?

States a specific resource (the reply thread under one comment) with a retrieval verb implied, and the phrasing clearly delimits it as a thread under a single comment rather than a post's top-level comments. It does not explicitly name instagram_postComments as the sibling it differs from, leaving that differentiation indirect.

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?

Gives concrete prerequisite routing: take comment_id from data.items[].id on /v1/instagram/post-comments, and explains why the post URL is still needed. It stops short of stating exclusions (e.g., use instagram_postComments for top-level comments), but the retrieval path is unambiguous.

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