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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds the critical 'Paid per call' cost signal and 'no local context' constraint, which are not in annotations. It does not contradict any annotation and provides useful operational context beyond what structured fields offer.

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, front-loaded with the core purpose and immediately followed by usage examples and expected returns. Every phrase earns its place—no redundancy, no fluff. The critical constraints (read-only, paid) are integrated naturally.

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?

There is no output schema, so the description compensates by listing return fields (severity, summary, affected ranges, fixed versions). It also covers the input alternatives and cost implications. Minor omissions like error handling or pagination are not critical for a lookup tool. Overall, it provides enough for an agent to call the tool correctly.

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 100%, so parameters are documented. However, the description adds interpretive value by explaining the either/or usage pattern: 'Give a CVE id (e.g. CVE-2021-44228) or a package+version.' This clarifies that cve and package+version are alternative query modes, which is not evident from the flat schema. It also explains the output fields, which are not in 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?

The description clearly states the tool's function: 'CVE / vulnerability lookup via OSV.dev' with specific input formats (CVE id or package+version) and expected outputs (severity, summary, affected ranges, fixed versions). This distinguishes it from siblings like paid_dns_intel or paid_crypto_price, which serve different domains.

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 provides clear context: 'Read-only, no local context. Paid per call.' This informs the agent about cost and safety. It doesn't explicitly name alternatives or exclusion criteria, but the tool's purpose is so specific that no ambiguity exists. The 'Give a CVE id or a package+version' clause implies when to use which parameter combination, which is actionable.

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