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

Annotations already signal it's a mutation (readOnlyHint=false) and non-destructive. The description adds real behavioral value beyond that: replace-not-merge semantics, the critical rule to pass existing R2 media URLs for unchanged assets, and the thread-chain replacement nuance for X/Threads (root stays segment 1). It stops short of stating whether an empty target array removes a platform target.

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 sentences with zero filler: the first fronts the action, the second delivers the media-reuse rule, the third covers the thread-chain exception. Every sentence earns its place.

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 tool with 11 required params, deep nesting, and no output schema, the description surfaces the three operational traps that would most likely break an agent call: replace semantics, R2 URL reuse, and segment ordering. Gaps remain (empty-array removal behavior, the fact that all target arrays are required means callers must reconstruct the full target set), but the description is strong relative to the enormous complexity.

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 bears the full burden. It explains the two semantically tricky parameters classes — media URLs (reuse R2 URLs) and twitter/threads segments (ordered array replaces whole chain) — but 11 top-level required params and their deep nested structures (poll, visibility, transform, scheduledFor variants) receive no elucidation anywhere.

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 the specific verb 'Replace' and names the exact resource ('an existing draft or scheduled post') plus the editable fields: caption, media URLs, schedule, and platform targets. This clearly distinguishes update_post from siblings like create_post, delete_post, and reschedule_post.

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 phrase 'existing draft or scheduled post' gives clear context for when to use the tool versus creating a new post, and implicitly excludes published posts. However, it never names alternatives explicitly or states conditions like 'use reschedule_post when only the date changes,' leaving some routing to inference.

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