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

With no annotations, the description carries the full burden, and it does well: the word 'Live' and the scorecard framing make clear this is a read-only observational call, and it discloses the auth requirement plus the demo/sample mode and that the sample is labelled. It stops short of stating rate limits, caching, or whether 'live' data is real-time or periodically refreshed.

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, front-loaded with the resource and its contents, followed by the call prerequisites. The middle enumeration is long but each item is a distinct reported metric, so it earns its space.

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?

With no output schema, the description compensates by enumerating what the scorecard returns, which is exactly what an agent needs to decide whether to call it. Remaining gaps are the default window and the tension between 'Needs the workspace key' and the schema declaring zero required parameters, which an agent must resolve on its own.

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 67%, so the schema already documents key and demo; the description mainly restates them, adding only 'tz_live_…' format detail and that the demo output is a labelled sample. The 'window' parameter, whose enum values (24h/7d/30d/all) have no schema description, is only implicitly referenced by 'per window' with no explanation of default or the difference between 'all' and '30d'.

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 names a specific resource (a live value scorecard for a TokenZero workspace) and enumerates the contents: savings, ROI, engine contribution, speed, parity, availability, privacy posture, per-model breakdown and recommendations. That makes the tool's identity unmistakable, though it never explicitly contrasts itself with siblings like audit_repo_token_waste or calculate_model_arbitrage.

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?

It states the authentication requirement ('Needs the workspace key (tz_live_…)') and gives an escape hatch ('pass demo: true for a labelled sample'), which is useful call-time guidance. However, it offers no when-to-use/when-not guidance relative to the sibling tools, so the choice between this and audit_repo_token_waste or calculate_model_arbitrage is left to inference.

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