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

Annotations already declare readOnly/idempotent/non-destructive, so the description's added value is elsewhere: it discloses result ordering (newest first) and two non-obvious semantic gotchas — mime_type is inferred from the filename rather than authoritative, and used_bytes is account-wide rather than project-scoped. That account-wide caveat is exactly the kind of context annotations cannot carry.

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?

Four short sentences, front-loaded with the action and ordering, then the disambiguation, then the two field caveats. Nothing is repeated from the schema and no sentence is filler.

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, so return values need not be enumerated, and the annotations cover the safety profile. The description still adds the ordering, the sibling disambiguation, and the two field-semantics caveats an agent needs to interpret results 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% and all three parameters (project_id, page, limit) carry their own descriptions with defaults, so the schema already does the heavy lifting. The description adds nothing about parameter behavior such as what happens when page exceeds the result set — baseline 3 is correct.

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?

Specific verb+resource: lists files in a project's media library, newest first. It also explicitly rules out a confusable sibling by stating 'These are uploaded assets, not source files', which lets an agent distinguish this from projects_files_list without opening either 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?

The 'uploaded assets, not source files' clause gives clear context for choosing this over the source-file listing tools, and the newest-first ordering hints at feed-style use. It stops short of naming alternatives (projects_files_list, projects_media_read) or stating exclusions explicitly.

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