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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: deterministic in-memory calculation with no API keys, and unknown model IDs falling back to the flagship baseline instead of erroring. It also names the returned artifacts (cost ratios, endurance matrix, recommended model ID), though it does not detail the endurance matrix's shape.

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 purpose and scope are front-loaded, and every sentence carries information: purpose, determinism, fallback behavior, aggregation rule, return artifacts, then sibling routing. It is dense but slightly overpacked, with the arithmetic details competing against the usage routing in a single block.

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?

There is no output schema, and the description compensates by naming the return artifacts (cost ratios, endurance matrix, recommended production model ID). With only three optional parameters, full schema coverage, and rich annotations, nothing an agent needs in order to call this 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 baseline is 3. The description goes modestly beyond the schema by explaining that burned_usd and remaining_usd are summed into a total session pool and that remaining turns are projected against a $137.45 reference budget, which clarifies how the two dollar parameters interact rather than restating them.

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 first sentence gives a specific verb and resource: it evaluates LLM rate-card tiers to quantify relay downgrade risk, cost ratios, and remaining coding session turns. It also names the siblings it is not (reconcile_usage_receipt, check_context_cliff, optimize_prompt_cache_layout), so an agent can distinguish it without opening any schema.

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?

It states the triggering conditions explicitly: 'comparing session burn rates or suspected relay throttling.' It then routes three named alternatives to their own scenarios (single invoice lines, prompt-length surcharges, mid-prompt cache breakpoints), which is exactly the when-to-use versus when-not guidance the dimension rewards.

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