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

Annotations already cover readOnly/idempotent/non-destructive/closed-world, yet the description still adds real context: 'Stateless in-memory calculation requiring no authentication and mutating no router settings,' plus the linear cost-scaling rule and the shadow-comparison behavior when has_custom_router_config is true. That is behavior beyond what the annotations declare.

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 sentences, front-loaded with the purpose, then constraints, output shape, and sibling routing. Every sentence carries useful information, though the density of jargon ('grant pools', 'warm-cached GA models', 'custom_router_mutex_check') makes it heavier to parse than necessary.

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 compensates by naming the returned fields (custom_router_mutex_check, six_turn_cost_breakdown with 1 cold write + 5 warm read turns, net_saved_usd) and their sign convention. Combined with auth, statelessness, and the shadow-mode caveat, an agent has everything needed to call and interpret it.

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 baseline is 3, but the description adds meaning the schema does not: cost 'scales per-turn cost linearly with context_tokens relative to current_model' and has_custom_router_config producing shadow comparison 'rather than active target IDs.' It does not add anything further about task_instruction's classification tiers, so it is strong but not exhaustive.

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 opens with a specific verb and scope: 'Simulates a 6-turn coding workflow cost projection comparing unrouted flagship execution against tiered routing across grant pools and warm-cached GA models.' This immediately corrects the misleading name (auto_route_task_by_quality_tier sounds like an action) by making clear it is a simulation, so an agent can separate it from siblings like detect_model_downgrade_and_substitution.

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?

Explicit routing is given: 'Use this tool when planning multi-turn task allocation; use check_context_cliff for single-turn length checks or reconcile_usage_receipt for post-hoc invoice auditing.' Both the when-to-use condition and two named alternatives with their own conditions are stated, leaving nothing to inference.

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