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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description goes further by disclosing the underlying engine (IR Rehearsal + company context + optional Claude Haiku), a concrete cost (~$0.10), and the required input. The 'POST endpoint' note is transport-level and, since the result is a non-persisted simulation, does not contradict readOnlyHint.

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?

Four tight sentences, each front-loaded with the purpose first, then outputs, then engine/cost, then the input requirement. No filler; the enumeration of return fields is arguably redundant given an output schema but it doubles as scoping and stays compact.

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 two-parameter simulation with an output schema and full annotation coverage, the description supplies the cost, engine, required input, and what the score/outputs look like. The only omission is guidance on interpreting the 0-100 score or how it compares to sibling analyses, which is minor.

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 description coverage is 100% for both parameters (ticker example, draft_text length bounds), so the schema carries the semantics. The description only restates 'requires draft_text' and adds nothing about format, ticker validity, or cost-driving length. Baseline 3 is correct.

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 + resource + scope: multi-stakeholder narrative risk simulation for a draft NZX announcement, and names the exact stakeholder set (institutions, retail, media, analysts, regulators). That is enough to distinguish it from siblings like analyse_ir_draft, simulate_event, simulate_investor_qa and get_narrative_tracker.

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 implied by 'for a draft NZX announcement' plus the 'requires draft_text' note, which tells the agent the necessary precondition. However, no sibling is named and there is no explicit statement of when to pick this over analyse_ir_draft or simulate_investor_qa, so routing 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.