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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds behavioral context beyond annotations: it explains the tool is a resolver/mapper step in a workflow, requires the post to be 'already-resolved', and warns about ID formats (LinkedIn base64-style IDs). It doesn't describe pagination or return format, but for a read-only list tool with strong annotations, this is solid.

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 information-dense and front-loaded with the core purpose, but it is somewhat repetitive: the post_id guidance appears in both the description and the schema's post_id property description nearly verbatim. The account_id guidance is also duplicated in the schema. This redundancy makes the description longer than necessary, though every unique piece of guidance is valuable.

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 read-only resolver tool with 3 parameters and no output schema, the description covers the critical workflow context: when to use it, how to obtain the required post_id, how to handle multi-account ambiguity, and what not to pass. The offset parameter is left unexplained, and there's no mention of pagination or return shape, but the tool's role as a resolver is well contextualized. The sibling list shows related comment tools, and the description routes the agent appropriately.

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 67% (post_id and account_id have descriptions, offset does not). The description adds significant meaning beyond the schema: it explains how to obtain post_id from specific sibling tools (linkedin_search_posts -> result.id, etc.), what never to pass, and how to handle account_id when multiple accounts exist. The offset parameter is undocumented in both schema and description, which prevents a 5, but the description compensates well for the coverage gap.

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 states a specific verb and resource: 'List comments for an already-resolved post' to map a human reference to an exact comment_id. It clearly distinguishes this from comment mutation tools like social_update_comment or social_delete_comment. However, the title 'Posts: Resolve comment' is slightly ambiguous—it could be read as resolving a comment rather than listing comments for a resolved post—but the description clarifies the actual purpose.

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 gives explicit when-to-use guidance: use it to map a human reference like 'the comment from Sarah' to an exact comment_id before replying/reacting/editing/deleting. It also provides explicit alternatives: linkedin_list_post_comments and instagram_list_post_comments, and tells the agent to first resolve post_id. It even includes negative guidance on what never to pass (post text, author user ID, URL). This is exemplary usage guidance.

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