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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description's added value is the two-phase quote-then-commit protocol, the no-spend first call, and the warning that a sample approval is one-time and does not authorize recurring research. Those are meaningful traits beyond the annotations. It still leaves unclear how many credits a run may consume or what the quote response contains.

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 short sentences with zero filler, leading with the capability and then the call protocol. Every sentence carries a distinct, actionable constraint.

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 two-phase approval flow is well covered for a destructive, credit-spending operation with no output schema. However, four of six required inputs, including the revisionHash credential-like field, are unexplained, which is a real gap for a tool this complex.

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 0% across 6 parameters, so the description carries the burden. It explains only requestId (must repeat the same value) and approvedMaxCredits (must match the approved amount exactly). pipelineId, revisionId, revisionHash, and source are left entirely undocumented in both schema and description.

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 and resource: 'Prepare a fresh sample of at most five prospects from one selected pipeline source.' The bounded size and single-source scoping are concrete. It does not explicitly differentiate itself from the similarly named sibling read_pipeline_sample, which would have earned a 5.

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 clear procedural guidance: call once for a quote that spends nothing, then repeat with the same requestId and the exact approvedMaxCredits after the user agrees. That is strong when-to-use instruction. It stops short of naming alternatives or when-not-to-use conditions, so it is not a full 5.

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