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

Annotations already declare non-readonly, non-idempotent, non-destructive, so the safety profile is covered. The description adds real behavioral context: size cap, private storage, the returned id contract with post_message, and the visible consequence of an unattached upload ("listed apart in the thread as 'Not attached to a message'"). It does not warn about duplicate uploads despite idempotentHint=false, which keeps it off a 5.

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?

Dense and front-loaded: storage semantics, then format choice, then attachment workflow, then the usage gate. Every sentence carries information, though the packing of three clauses into the second sentence makes it slightly harder to scan.

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?

No output schema exists, so the description must convey return behavior; it does so via the returned id contract with post_message. Combined with the size limit, privacy, and attachment modes, the definition is nearly complete for a write tool with 0% parameter coverage, with mime_type handling being the main omission.

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?

With 0% schema description coverage, the description must carry parameter meaning and it does for the hardest part: text versus content_base64 as mutually exclusive alternatives, matching the oneOf, and message_id as optional attachment. It leaves mime_type and project_id entirely unexplained, so two of six parameters remain undocumented.

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 ("Store a real file privately") plus a hard constraint (1 MiB maximum), and distinguishes itself from get_file/list_files by implying write-vs-read. The "never a local path" clause further makes clear this uploads content, not a reference.

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?

Explicitly routes the agent: attach via message_id if a message exists, otherwise use the returned id in post_message attachment_ids straight away, referencing a named sibling. Adds a genuine when-to-use gate ("Upload only when requested"), which is rare and useful given the write annotation.

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