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

Annotations only say readOnlyHint=false and destructiveHint=false; the description adds substantial context beyond that — this call trains nothing and spends nothing, spending is gated behind an approval flow, and the job is capped at one candidate plus one diagnosed rerun. That is real behavioral disclosure an agent cannot get from the structured fields.

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 core purpose is front-loaded in the first sentence and each following sentence carries a distinct constraint (no train/spend, approval path, rerun limit). Slight redundancy remains, e.g. 'Scope: write' only echoes the readOnlyHint=false annotation, keeping it just short of exemplary.

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 6-parameter write tool with no output schema, the description covers purpose, non-effects, approval gating and cardinality limits well. It does not indicate what the call returns or how to follow up (e.g. get_training_job), which is a minor gap given the absence of an output schema.

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 every parameter including capUsd, method, projectId, customerId and rerunReason is already documented in the schema. The description restates the field list and the rerunReason requirement without adding format or edge-case detail, so it sits at the baseline for high-coverage schemas.

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 precise verb+resource ('Record the intent to train one candidate on the project's frozen dataset version') and enumerates the recorded fields (base model, method, spend cap). It is clearly distinct in substance from get_training_job and update_training_job_facts, but it never names a sibling, so differentiation is left to inference.

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?

Gives explicit prerequisites and alternatives: spend requires an approved training_spend approval via request_approval decided by a human or an approve-scoped key, and the actual training happens in an external runner. It also states the cardinality rule (one candidate plus one diagnosed rerun) and that the rerun requires rerunReason, so the agent knows the preconditions before calling.

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