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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is fully covered and the bar is lower. The description adds genuine behavioral context beyond annotations: the tool returns aggregates rather than raw records, splits par into new money versus refunding, and is restricted to primary-market issuance — a scope an agent must know before answering a question. No contradiction with the annotations.

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?

Three sentences with no filler: function and metrics first, example questions second, scope constraint last. Every sentence earns its place and the highest-value information is front-loaded.

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 read-only aggregation tool with three well-documented optional parameters and full annotation coverage, the description covers the essentials: what is aggregated, over which dimensions, and the set of returned metrics. The one gap is return shape — it doesn't state whether results are grouped as year×class rows or separate sections — but nothing an agent needs to invoke it correctly is missing.

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 100%, so the schema already documents top, since, and authority_class with defaults and formats, meeting the baseline. The description does tie parameters to aggregation dimensions (since ↔ 'by year', authority_class ↔ 'by authority class', top ↔ 'most active issuers'), but that mapping is modest and adds little beyond the 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?

Opens with a specific verb and resource: 'Aggregate New York public authority borrowing by year and by authority class', naming the exact metrics returned (total par, new money vs refunding, most active issuers). The three quoted example questions make intent unmistakable and implicitly distinguish this aggregates tool from siblings like ny_authority_debt_search and ny_authority_debt_profile.

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 quoted example questions ('how much did New York authorities borrow in 2024', 'which New York issuers borrow the most', 'how much of this is refinancing') give an agent clear positive signals for when this tool fits. The 'Primary-market issuance only' sentence adds an explicit scope boundary. However, it never names sibling tools or states when not to use it, so explicit exclusions and alternative routing are absent.

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