security-tools

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

With no annotations provided, the description carries the full burden and delivers thoroughly: it declares the operation non-destructive ('never logs in or changes anything'), read-only ('Reads only what the site serves publicly'), and specifies the output contract ('letter grade (A to F) plus specific findings'). It also signals that no credentials or login state are required, which is exactly the behavioral context an agent needs before invoking.

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, each earning its place: core function and output first, illustrative example questions second, and the read-only scope constraint last. There is no filler and no repetition of schema content. The most decision-relevant information (what it does and its safety profile) 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 tool with one fully-documented parameter, no annotations, and no output schema, the description covers everything an agent needs: purpose, return format (grade plus findings), example use cases, and the non-destructive read-only behavior. The absence of an output schema is mitigated by the explicit description of what the tool returns.

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%: the single `domain` parameter is fully documented in the schema itself ('a domain like example.com or a full URL'). The description merely reinforces this by using 'example.com' in its examples and adds no syntax, format, or edge-case details beyond the schema. Baseline 3 is correct because the schema does all the heavy lifting.

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 verb and resource ('Run a free front-end security check on any website') and names the concrete output ('a letter grade (A to F) plus specific findings'). The example questions ('is example.com leaking API keys or secrets', 'does this site expose a Stripe/AWS/OpenAI key') pin down the exact scope of the tool. No siblings exist, but the description is fully self-sufficient.

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 provides concrete usage scenarios through its example questions, letting an agent match a user request about leaked secrets or client-side security to this tool. Scope constraints ('Reads only what the site serves publicly; never logs in or changes anything') implicitly mark when it is not appropriate, such as authenticated or private testing. It stops short of explicit when-to-use/when-not-to-use framing, but with no sibling tools there is no alternative routing needed.

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