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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds behavioral value beyond these annotations: it warns that the active-project pointer is never used to guess, discloses that the result includes the project identity, and explains that unused uploads are surfaced and marked AVAILABLE. This helps the agent avoid misinterpreting scope or assuming active context propagation. No contradiction exists.

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?

The description is front-loaded with the crucial scoping constraint ('PROJECT-SCOPED') and every sentence carries distinct, useful information: scope, inclusion of unused uploads, kind semantics with downstream pairings, and the AVAILABLE marker. It is dense but not wasteful, though it is slightly longer than strictly necessary.

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?

Given there is no output schema, the description goes a long way toward explaining what to expect: project identity in the result, per-kind asset categories, storage_key relevance, and the AVAILABLE marker for unused files. It does not specify the full result shape (e.g., whether it's an array, what other fields each asset has), but for a read-only listing tool backed by readOnlyHint annotations, the provided detail is sufficient for an agent to decide whether to call it and what to do with the data.

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 only 50% because the `kind` parameter has no schema-level description. The tool description compensates by explaining each enum value semantically and linking them to companion tools: 'music' for audio, 'clip'/'image' for use with insert_media, 'render' for past renders, and 'all'. The `project_id` parameter is already well described in the schema, and the description reinforces its immutable-scope nature.

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 states a clear verb ('lists') and resource ('assets' in a project), and explicitly scopes the action: 'PROJECT-SCOPED: this call acts only on the explicit project_id'. It further differentiates from sibling tools by describing exactly what is included ('used on the timeline AND unused uploads') and by clarifying that the active-project pointer is never used, which distinguishes it from tools that rely on current context.

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 description gives concrete guidance on how to interpret and use results: it maps `kind` values to downstream tools ('use its storage_key with add_music or add_voiceover', 'use with insert_media'), and explains that unused files are marked AVAILABLE and can be placed without re-uploading. It also tells the agent where to source `project_id` from (list_projects/open_project/project_state). It lacks an explicit when-not-to-use or named alternative, but the context is clear enough to route an agent.

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