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

Annotations establish write/non-idempotent/open-world, and the description adds genuinely new behavioral context: the mandatory two-step resolve-then-edit pattern and the warning that LinkedIn IDs are preformatted/base64-style, which is non-obvious. It does not disclose authorization requirements (e.g., must own the post) or that can_comment changes audience visibility, so it falls short of a 5. No contradiction with annotations.

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 resolution-first instruction is front-loaded, which is correct, but the entire post_id block ("Post ID: Exact provider post id; LinkedIn commonly uses...") is repeated word-for-word from the input schema, and the resolver list is jammed into one run-on line. Redundancy costs it points.

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 non-idempotent write with no output schema and 4 parameters, the ID-resolution story is well covered but several things an agent needs are missing or only in the schema: the multi-account disambiguation flow (account_id), the meaning of can_comment, and whether the editing user must be the post author. Adequate, with clear gaps.

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 75%, so the baseline is 3. The post_id guidance in the description is largely a verbatim duplicate of the post_id schema description rather than added meaning, and it says nothing about `text` semantics or what the `can_comment` enum values actually change about the post. Marginal added value over the schema.

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 opens with a specific verb+resource ("Edit an existing supported social post"), which cleanly separates it from social_update_comment, social_delete_post, and linkedin_create_post. The word "supported" leaves the provider scope slightly fuzzy, though the resolver list (LinkedIn, Instagram) implies it. Strong but not a perfect sibling disambiguation.

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?

It gives an explicit workflow: resolve the post first, then reuse post.id, and it names the resolver tools (linkedin_search_posts, linkedin_list_user_posts, instagram_list_user_posts). The "Never pass: post text, author user ID, URL" rule is a clear negative constraint. It stops short of naming when NOT to use this tool (e.g., comment edits vs. post edits), so it is a 4 rather than a 5.

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