Runtime advisories

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

Annotations already declare readOnlyHint=true, openWorldHint=false, idempotentHint=true and destructiveHint=false, and the trailing 'Offline.' corroborates the no-network behavior while adding that inputs come from local files or headers the caller already holds. Beyond that, the description says nothing about what a finding looks like or how results are shaped, which matters because there is no output schema. With annotations carrying the safety profile, this is adequate but thin.

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 question the tool answers, then the two input modes. Firmly efficient with no filler. The phrasing of the opening question is slightly convoluted ('Is the PHP, nginx, Apache... an app runs affected by'), and the trailing 'Offline.' is a fragment, though both are informative rather than wasteful.

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 tool with a nested-object parameter and no output schema, the description covers inputs well but says nothing about returned findings — no mention of severity vocabulary, advisory identifiers, or what an end-of-life entry looks like. The agent knows how to call it and what it answers, but not how to interpret or present the response.

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 baseline would be 3; the description earns a step above by explaining that the path parameter triggers reads of Dockerfiles, compose files and version pins rather than arbitrary source, and by illustrating the headers use case with real header names. The meaning of max_findings is left entirely to the schema, which already documents severity ordering and the default.

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 the exact resources checked (PHP, nginx, Apache, Node.js, Python, OpenSSL), the two questions asked (published advisory vs. end of life), and the evidence sources (Dockerfiles, compose files, version pins, response headers). That is far more specific than the title alone. It stops short of differentiating itself by name from siblings such as check_dependencies or scan_url, leaving the agent to infer that this covers runtimes rather than packages or live URLs.

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 gives concrete invocation paths: supply a project path when you have a repo, or supply response headers you already collected. The parenthetical about Dockerfiles/compose/pins tells the agent what the path scan will look at. It offers no explicit when-not guidance or named alternative tool, so the boundary against dependency scanning and URL scanning is only implied.

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