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

The description discloses several behavioral traits beyond what annotations provide: nothing trains until paid, the returned job_token is the sole credential (and must be stored), trained models are benchmarked and publicly listed permanently unless private=true, and private models add 500 credits. These are non-obvious behaviors that the agent needs to know, and annotations (readOnlyHint=false, destructiveHint=false) do not cover them. No contradiction with annotations.

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 description is dense but well-organized, with key alerts like 'STORE IT' and 'PICK A TIER' front-loaded. It uses bold-like emphasis (via caps) to highlight critical points. Every sentence adds value, though it is slightly long. Not a 5 because it could be trimmed slightly without losing meaning, but it is far from verbose.

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?

The description explicitly covers the return value (job_token and price), the free-until-paid nature, tier selection guidance, privacy implications, and benchmark listing. With no output schema, this is sufficient for an agent to call the tool correctly. Minor gaps exist (e.g., error handling, retry logic), but they are not critical for a quoting tool.

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 parameters are already well-documented in the schema. The description adds extra semantic context beyond the schema, such as pricing comparisons ('~2x the search', '60-95 CHF'), the 'validated recipe' for tiers, and the note that the same options exist on the website. This adds moderate value, justifying a 4 rather than a 3.

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 states a specific action ('Quote a wake-word training job'), clarifies it's free and nothing trains until paid, and explicitly says it returns a job_token and a price. This differentiates it from siblings like pay_training_job and get_training_job, making the tool's purpose unmistakable.

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 gives clear when-to-use guidance: it tells the agent to pick a tier, explains when to choose each tier (standard for almost every request, best for hard words, studio only after a standard job disappointed), and notes that the quote is free until payment. It also mentions confirming expensive prices with a human first, effectively excluding use cases where payment is intended.

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