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

Annotations only declare readOnlyHint=false, so the description carries the burden and does so well: it discloses the state transition to awaiting_tp, the eligibility rules that cause refusal, and the retention of business_facts until the reviewer is erased. The Defamation-specific meaning of those facts is extra context an agent could not infer from any structured field.

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 is front-loaded in the first sentence and the remaining sentences each add a distinct constraint (state, refusals, retention). The inline qualifiers 'ref, optional,' and the trailing '(capability: cases.mark_filed_own)' are slightly awkward but cost little.

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 mutation tool with no output schema, the definition covers the state machine around the call, the refusal rules, and what happens to the supplied facts, which is what an agent needs to decide whether to invoke it. It does not say what a successful response looks like or whether any authorization beyond the stated capability is required.

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 has to compensate, and it does for the two ambiguous fields: ref is constrained to Trustpilot's case/ticket number pattern and explicitly ruled out as a note, and business_facts is tied to what was passed to appeal_packet plus its retention and Defamation semantics. case_id and sent_at are left to the schema, which is a minor gap given how self-evident they are.

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: recording that an appeal was filed through Trustpilot's appeal form against a kept-online decision. It also distinguishes itself from the neighbouring record_decision step and from appeal_packet, so an agent can place it in the workflow without opening 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?

It states the post-condition (the case returns to awaiting_tp until record_decision is called) and two explicit refusal conditions: a second appeal, and more than six months after the decision. What is missing is a positive instruction that appeal_packet must precede it; the link is only implied by 'as you passed them to appeal_packet'.

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