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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the description is free to add other context — and it does: an API key is required, and the result is a merged set of the org's own published claims plus library-matched best practices rather than a raw claim list. It still doesn't mention pagination or result-size behavior, which keeps it short of a 5.

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 with the core capability front-loaded and the auth requirement last. 'This is the bridge between OTP and your agent army' is the weakest sentence — motivational framing rather than operational information — but it is short and does signal intended consumer.

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 some burden for describing the return, and it only says 'rules in a format agents can directly use for coordination' — the shape, size, and per-rule fields are unknown. Safety, auth, and composition are covered, and all three parameters are optional, so an agent can call it, but it can't predict what comes back.

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 schema already documents section, min_confidence, and include_best_practices fully — baseline 3. The description does add one piece of meaning by explaining that best practices are merged in by default ('PLUS matched best practices'), which contextualizes the include_best_practices toggle. The filtering parameters go unmentioned in prose.

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?

States a specific verb and resource ('Get your organization's operational rules') and clarifies the composition: published OOS claims plus matched best practices from the library. This composition detail implicitly separates it from get_claims and get_best_practices, which each return only one half. Jargon (OTP, OOS) and the 'agent army' framing slightly blur the meaning, but the retrieval target is unmistakable.

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?

Usage is only implied — 'Returns rules in a format agents can directly use for coordination' suggests the context (an agent needs actionable rules) but never states when to choose this over get_claims, get_best_practices, or export_rules_markdown. There are no exclusions or prerequisites beyond the API key note. An agent must infer the selection criteria from the sibling names.

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