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

Goes beyond annotations meaningfully: partial-failure semantics ('failed' list with reasons, saved ones need no retry) are exactly the retry guidance an agent needs given idempotentHint=false, and the 50MB/10-file limits plus 'uses the account's storage' disclose quota side effects. It still doesn't state auth or permission requirements.

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?

Front-loads the action and the return contract, then folds constraints and the downstream call into single dense clauses. Every sentence carries actionable information; nothing is restated from the schema.

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?

Output schema exists and annotations declare the mutation profile, yet the description still supplies the failure/retry contract that neither covers. Combined with format limits and the follow-up tool to call, an agent has everything needed to invoke and chain it 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 100%, so baseline is 3; the description adds real value with accepted MIME types, per-file size cap, and the 10-per-call ceiling that the schema only partially encodes via maxItems. It does not explain the individual `files` fields (file_id vs download_url) beyond what the schema already says.

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 verb and resource ('Save images or videos the user attached... into their PostNext asset library') and scopes the input to user-attached message media, which implicitly separates it from generic asset tools like upload_asset. An agent can tell what it does and what it produces without opening the schema.

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 a clear trigger ('Use this when the user has attached a photo or video and wants it in a post') and hands off to create_post_draft/update_post_draft with the returned url in `mediaUrls`/`media`. It does not address when to prefer upload_asset or request_asset_upload instead, so the sibling routing is incomplete.

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