draft_evidence_pack

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 real value beyond that by specifying the artifact is plain text, that it is a draft, and that a human submits it afterwards — clarifying that this tool does not itself file the chargeback. It says nothing about the pack's contents or size, which keeps it from a 5.

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 sentence is front-loaded and the remaining lines are compact argument documentation with no filler. The 'Args:' block is slightly boilerplate but each line carries information the schema lacks.

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 only two parameters and an output schema present, the description need not explain return values, and it covers what it must: intent, the human-review boundary, and both arguments. The remaining gap is what the evidence pack actually contains and how failures (e.g., unknown dispute_id) surface.

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%, so the description must carry the parameters, and it does: dispute_id gets a concrete format example (DSP-201) and as_of gets both a format (YYYY-MM-DD), a semantic ('date to count days left from'), and a default of today. The 'days left' phrasing usefully hints the pack contains a deadline countdown, though the dispute_id example is a format sample rather than true meaning.

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 opens with a specific verb and resource: 'Draft a plain-text evidence pack for a chargeback,' and adds the crucial qualifier that the output is for human review and submission. That distinguishes it in intent from triage_dispute or list_open_disputes, though it never names those siblings explicitly.

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?

Usage is only implied: 'for a person to review and submit' suggests this is the step after triage and before submission, but the description never states when to call it versus triage_dispute, list_open_disputes, or explain_reconciliation_break. No preconditions (e.g., dispute must be open) or exclusions are given.

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