record_action

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

With no annotations provided, the description carries the full burden and delivers: it discloses the side effect ('writes the plugin's metadata key on each asset'), scopes it ('other apps' keys are untouched'), and explains partial-failure semantics ('Success is true only when nothing failed', with a failed array of {asset_id, error}). This is exactly the behavioral context an agent needs.

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?

Purpose is front-loaded in the first sentence, the side effect follows immediately, then a tight Args/Returns structure. Every sentence earns its place — the examples in Args serve as operational guidance, not padding.

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 schema descriptions, the description is complete: purpose, side effects, parameter semantics, return format, and success criteria are all covered. The only minor gap is whether the metadata key is overwritten or appended on re-record, which is negligible against the overall coverage.

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 compensate — and it does. The Args section gives all three parameters real meaning: asset_ids ('the assets the action touched'), action with example labels ('added_to_album', 'date_fixed', 'rotated'), and detail with concrete content guidance ('album name, previous value, the user's request'). Fully compensates for the bare schema.

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 ('Remember something the plugin did to assets') and names the purpose ('for audit or undo'), with concrete examples of what gets recorded. This clearly positions it as a logging/audit tool distinct from the many sibling mutation tools (rotate_assets, tag_assets, delete_assets) and undo tools (restore_assets, revert_asset_edits).

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 clear context for when to use it: after the plugin changes assets, to preserve prior state and rationale for audit or undo. The examples (which album, previous date, why rotated) make the trigger scenario concrete. It doesn't explicitly name exclusions or alternative tools, but no sibling fills this recording role, so the context is sufficient.

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