describe_project_assets

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

No annotations are provided, so the description carries the full burden. It usefully discloses that this is an async job to poll and that vision labels require a configured endpoint, plus a behavioral guardrail ('Never claim content recognition from filenames alone'), but leaves failure modes, outputs, and side effects unaddressed.

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 plus a workflow clause, front-loaded with the core action and free of filler. Slightly dense, but every sentence carries actionable content.

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 3-parameter tool with no annotations and no output schema, the description covers the workflow and one key precondition but omits parameter meaning and return behavior. Adequate but with clear gaps.

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 3 parameters and 0% schema description coverage, the description must compensate but largely does not. It gestures at 'provider' and 'allow_remote'-style concepts ('Optional vision labels require a configured endpoint') but never explains what paths, allow_remote, or use_provider actually control.

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 ('Capture') and resource ('model thumbnails and metadata'), which is clear. It doesn't explicitly distinguish itself from the many sibling asset tools, but the asset-description focus is inferable.

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?

Provides concrete routing: 'Without a provider, poll this job, call get_asset_evidence... then save_asset_description', and notes optional vision labels require a configured endpoint. It names the alternative tools to chain with, though it never states when NOT to use this tool.

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