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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the bar is lower. The description adds genuinely new behavior: results are ordered 'recent files first' and capped 'up to 100', and that it returns 'metadata' rather than file contents — an important distinction from get_file.

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?

Two sentences, zero padding, with the core operation front-loaded before the optional filter and the ordering/cap detail. Every clause 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 simple read-only list tool with full annotation coverage and no output schema, this is nearly sufficient. The remaining gap is what fields 'metadata' actually contains and what happens beyond the 100-item cap, but neither blocks correct invocation.

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 must carry the load. It clarifies message_id as an optional single-message filter and hints at the limit behavior ('up to 100'), but never explains that limit defaults to 30, and project_id is left entirely unexplained.

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 — 'List private file metadata for a project' — plus an explicit scope qualifier (optionally per-message). This clearly separates it from get_file (single file) and upload_file, though it does not name or contrast with those siblings directly.

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?

'Optionally restricted to one message' implies the when-to-use case for message_id, but there is no guidance on when to prefer this over get_file or list_messages, and no stated prerequisites beyond the required project_id.

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