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

Beyond the annotations, the description discloses rich behavioral details: the returned OSV fields, the nested `database_specific.openvuln` structure, live EPSS reads from FIRST, CISA KEV semantics, null behavior for checked-and-absent KEV data, `unstated` meaning in AI benchmark results, source attribution per field, and the explicit guarantee that no exploit code is included. These details materially help an agent interpret and trust the response.

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 front-loaded with the core purpose and then efficiently enumerates return fields in a dense but information-bearing manner. It is lengthy and uses a semicolon-heavy structure rather than separate sentences, but given the absence of an output schema, the detail mostly earns its place.

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 and only safety annotations, the description carries the full burden of explaining what is returned and does so comprehensively, including field names, nested structures, status values, and source attribution. An agent has enough information to call the tool and interpret its response 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 the schema already documents the single `id` parameter, but the description adds substantial semantic value by listing the broad range of accepted vulnerability ID formats including MAL and NDB beyond the schema examples. This helps an agent know that non-CVE identifiers are valid inputs.

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 states a specific resource and scope: 'Everything known about one vulnerability, as an OpenVuln record (a valid OSV record).' It clearly distinguishes the tool from generic lookup siblings by naming the record format and accepted vulnerability ID families. An agent can immediately understand this returns comprehensive vulnerability data.

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 clear invocation context by specifying that the agent must provide an `id` and enumerating accepted ID types such as CVE, GHSA, OSV, PYSEC, GO, RUSTSEC, MAL, and NDB. It does not explicitly state when to use this versus alternatives, but the purpose is unambiguous enough that no close sibling competes for the same task.

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