Breaches for an email (needs HIBP key)

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

Annotations already establish readOnlyHint and openWorldHint, and the description adds operational context they cannot carry: the server-side HIBP_API_KEY prerequisite and the degraded/alternative behavior when it is absent. The ethical-use constraint on whose addresses may be checked is likewise beyond the annotation set. It still omits rate-limit behavior for the external HIBP call.

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 short sentences, each carrying distinct information (what it returns, the key prerequisite and fallback, the authorization constraint) with the resource statement front-loaded. Slightly telegraphic phrasing ('otherwise explains alternatives') costs a little clarity but not length.

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, yet the description never indicates what a result contains (breach names, dates, exposed data classes) or the shape of an empty/unauthorized response. For a single-param read tool the prerequisites and constraints are well covered, but the return contract is a real gap.

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?

One parameter at 0% schema description coverage, so the schema shows type and format but no meaning. The description implies a single owned/authorised address but adds no format, normalization, or multi-address guidance, leaving most parameter semantics to the format hint alone.

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?

Names the specific resource (breaches) and the selector (an email address), so an agent knows this is the email-keyed breach lookup. It does not differentiate itself from the close sibling domain_breaches or breach_details, leaving the agent to infer that this one keys on an address rather than a domain.

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 an authorization condition ('Only check addresses the user owns or is authorised to check') and notes a fallback when no API key is configured, which is real usage guidance. However, it never states when to pick this over domain_breaches or breach_catalog, so the choice among siblings is left to inference.

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