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

Annotations already cover the safety profile (readOnly, idempotent, non-open-world), so the bar is lower; the description still adds real context by disclosing the MTTF fallback to 'Meta's published 2024 reliability data' and the async-checkpointing caveat. It doesn't cover error conditions, but for a pure computation tool that is minor.

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?

Two sentences, front-loaded with the purpose and method, followed by a compact enumeration of return values. The second sentence is dense but every listed output earns its place given there is no output schema.

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 the full burden of describing returns and does so completely: recommended interval, expected failures per day, GPU time wasted at recommended vs current intervals, and daily saving. Inputs are fully documented in the schema, so nothing needed for correct invocation 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 description coverage is 100%, so all six parameters are already documented with ranges and defaults; baseline is 3. The description names GPU count, checkpoint write time, restart time and MTTF as the driving inputs and restates the MTTF fallback, adding marginal but not new detail.

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 (recommends), resource (checkpoint interval for a training job) and the underlying method (Young and Daly formulas). It is unmistakably distinct from siblings like analyze_nccl_benchmark or calculate_fabric_degradation_cost without needing to open the 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?

The description implies usage (plan checkpointing for a training job given GPU count, write time, restart time, MTTF) but never states when to prefer this tool, when not to use it, or names an alternative. The MTTF-estimation fallback is the only conditional guidance offered.

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