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

Annotations already declare this a read-only, closed-world operation, so safety disclosure is covered. The description adds real context about what the payload contains (message interpretation, asking protocol, human-step handoff for sign-ins/clicks/payments, reporting) and that a situation string reorders relevance. It stops short of saying how large or structured the returned rules are, which matters for an agent deciding how to consume them.

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, both front-loaded with the actionable instruction before the enumeration of returned content. The parenthetical examples and the task-scope list are dense but each clarifies behaviour rather than padding. Slightly heavy clause stacking, but nothing is wasted.

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, the description carries the burden of describing the return, and it does so by enumerating the four content areas an agent will receive. What is missing is only secondary: whether the guidance is stable across calls, whether the situation string changes content or merely ordering, and roughly how long the response is.

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% and the single optional parameter is already documented with examples in the schema. The description's addition is that the situation string affects ranking ('most relevant rules first'), which is a genuine semantic gain but modest. Baseline 3 is appropriate given the schema carries most of the load.

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 gives a concrete action and payoff: call once at the start of working for a person and it returns rules for interpreting their messages, asking questions, handing off manual steps, and reporting. The scope clause ('a site, a database, a domain, a document, not only UI') usefully widens the applicability. It does not explicitly distinguish itself from near-neighbours such as ihumane_get_rules or ihumane_get_check, so sibling differentiation is left to inference.

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?

'Call this once when you start working for a person' is an explicit trigger condition plus a frequency constraint, which is exactly the guidance an agent needs. 'Pass a situation to get the most relevant rules first' explains when to supply the parameter. There is no when-not-to-use statement and no named alternative for later rule lookups.

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