breachPastes

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It goes beyond the basic operation by revealing that the tool depends on a paid API endpoint and requires HIBP_API_KEY. This is a meaningful prerequisite and cost/access implication that an agent must know. It also clarifies that the search targets publicly posted pastes, setting expectations about scope. However, it does not mention rate limits or error handling, which would be valuable but not essential for a simple read-only search.

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 consists of two concise sentences. The first sentence front-loads the primary action and purpose. The second adds a critical prerequisite without unnecessary detail. Every word earns its place, with no fluff or repetition.

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?

The tool has one parameter and no output schema, so the description is responsible for explaining not just purpose but also what the caller can expect. It clearly covers purpose, source, and authentication. However, it fails to disclose the return format (e.g., a list of paste URLs or an empty result) or possible failure modes (e.g., no matches, invalid key). Given no output schema exists, this omission leaves the agent uncertain about how to handle the response, making the description incomplete for a self-contained tool.

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?

The input schema already has 100% coverage: the 'email' property includes a description ('The email address to search for in pastes'). The tool description repeats the same concept without adding new meaning. No additional parameter semantics, such as format requirements or expected input examples, are provided. The baseline of 3 is appropriate because the schema does the heavy lifting and the description adds no extra semantic value.

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 action ('Search for an email address'), the resource ('publicly posted pastes (Pastebin, etc.)'), and the service ('via HaveIBeenPwned'). This is a specific verb+resource+scope construction that distinguishes it from sibling tools like breachList or breachSearch, which cover broader breach data. The mention of 'Pastebin, etc.' further scopes the tool's purpose.

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 implies usage context: when you need to find whether an email appears in pastes. It does not explicitly list exclusions or alternative tools, but the phrase 'Search for an email address' makes the trigger condition clear. The added prerequisite 'Requires HIBP_API_KEY (paid endpoint)' provides important context about when the tool can be used (i.e., only when the key is available). No explicit alternatives are named, so it doesn't reach the highest bar.

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