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

Annotations already declare readOnlyHint: true, and the description consistently builds on this by disclosing auth requirements ('Authenticated'), file delivery ('Parquet, full-history files fetched by YOUR code, not returned inline'), giving agents valuable behavioral expectations. No contradiction with annotations, and adds detail beyond them.

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 tight sentences front-load the purpose and structure surpluses well. The second sentence is slightly dense ('Parquet, full-history files fetched by YOUR code, not returned inline'), but it earns its place by disclosing fetch semantics without waste.

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 2-parameter tool with an enum and a vintage, the description covers purpose, file types, fetch behavior, and authentication in minimal space. It doesn't explain the exact contents of each file in depth, but it gives a complete enough mental model for an agent to decide which file it wants.

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 50% (vintage documented). The description compensates for the cryptic file enum by explaining what the two bundles contain ('patent-level innovation measures (citations, originality/generality...) or the assignee-year panel'), which is useful. Yet it doesn't add detail on the 'vintage' format beyond the schema's own text.

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?

Clear and specific: 'Authenticated download instructions for an IP Data Library bundle' names the verb, resource, and the two library variants ('patent-level innovation measures' or 'the assignee-year panel'). Distinguishes from sibling download tools via the Parquet/ElkassabgiData context.

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?

Implies usage through context like 'omit for the newest' and 'vintage from list_ip_bundles', and 'same ElkassabgiData key as every family library' hints at shared auth. However, it never explicitly says when to use this versus sibling downloaders like get_hf_download_link or list_ip_bundles, nor when not to use it.

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