set_browser_item_metadata

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

With annotations only indicating non-read-only and non-destructive, the description adds substantial behavioral context: a plan/edit two-phase flow, exact revision requirement, single-use confirmation token, and that it avoids modifying Live's native collections. This goes beyond the annotations and helps the agent predict side effects and workflow.

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 two sentences with zero waste. The first sentence front-loads the action, resource, and workflow semantics; the second adds a critical scoping constraint. Every word contributes to understanding, and the structure is easy to parse at a glance.

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?

The tool is non-trivial (8 parameters, two-phase plan/confirm flow, no output schema), but the schema already covers all parameter semantics and the annotations cover safety. The description supplies the overall conceptual frame but leaves the step-by-step dry-run-then-confirm sequence to be inferred from the schema's dryRun, planHash, and confirmationToken descriptions. This is sufficient, though it could explicitly spell out the call sequence.

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?

Although schema coverage is 100%, the description's phrasing 'exact Live item identity, revision, and single-use confirmation' groups the key parameters (root/path, expectedMetadataRevision, planHash/confirmationToken) into a coherent mental model. It adds meaning beyond the isolated schema field descriptions by explaining why these parameters exist together.

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 clearly states the tool's action ('Plan or edit'), the resource ('private MCP-managed browser tags and favorite state'), and key constraints ('exact Live item identity, revision, and single-use confirmation'). It also distinguishes the tool by noting it 'does not modify Live's native collections', giving the agent a specific mental model of its scope.

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 no explicit guidance on when to use this tool versus alternative tools like get_browser_item_metadata or set_preset_metadata. The only exclusions are a negative constraint ('does not modify Live's native collections') and no mention of prerequisites or decision rules, leaving the agent to infer usage context from the schema.

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