Log10x orientation

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

Annotations already declare readOnlyHint/idempotentHint/openWorldHint, but the description adds substantial context beyond them: it runs three live probes, is safe on any boot state including an unconfigured env (skips probes, assumes Dev CLI tier), and defines the envelope contract (must_render_verbatim, must_ask_user, forbidden_next_actions). It also explains the siem_lens what-if behavior and how siem_actual vs siem_lens are stamped. No contradiction with the read-only annotation.

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 critical directive ('CALL THIS FIRST') is front-loaded, and almost every clause carries real information (probes, tier detection, envelope fields, gating). It is dense and delivered as one long run-on paragraph with nested parentheses, which hurts scannability, but little content is genuinely 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?

For a complex orchestrator that gates all downstream tool calls, the description covers edge cases (unconfigured env, session_state midway/returning) and the envelope contract. An output schema exists, yet the description still names the key return fields the agent must honor, so nothing needed to invoke and act on it correctly is missing.

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 all three enum parameters; the baseline is 3. The description adds genuine value on top by stating the default when intent_hint is omitted ('treated as orient') and by instructing the agent to carry siem_lens onto follow-up cost/forensic calls, which is cross-tool semantic guidance the schema does not provide.

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 function: it orients a session by detecting tier via three live probes and the SIEM, then returns a structured orientation envelope. It clearly positions itself as the entry point ('CALL THIS FIRST ... before any other tool') and distinguishes itself from the many sibling analysis/action tools by being the read-only orientation step rather than a data query.

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?

Gives explicit when-to-use triggers ('open-ended cost question', 'save X%', 'where do I start'), an explicit ordering rule ('before any other tool'), and exclusions via `forbidden_next_actions`. It also names the alternatives the agent should carry forward to (cost_options, estimate_savings, top_patterns, savings) and describes session_state fresh/midway/returning semantics, so routing is unambiguous.

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