ProofMart

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behaviour, so the safety profile is covered. The description adds information the annotations do not: zero authentication ('no key needed') and no metering cost, which materially affects whether an agent should hesitate before calling.

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?

Two tight sentences: the payload description is front-loaded, followed by the cost/auth reassurance and then the usage trigger. Nothing is redundant and nothing is missing.

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 no parameters, no output schema, and full annotation coverage, the description carries little burden. It names the returned fields (bundle, price) and the access conditions, though it stops short of describing ordering, plan tiers, or response shape in any detail.

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?

The tool takes zero parameters, so the baseline is 4. The description correctly implies a no-argument, whole-catalogue call and adds no misleading parameter cues.

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 what the tool returns: every plan's monthly check bundle and draft price, framed as 'the ProofMart menu'. The verb 'list' comes from the name rather than the text, but the resource and payload are unmistakable and the unrelated sibling (verify_claim) needs no explicit differentiation.

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?

'Useful when an owner asks what subscribing would get them' supplies a concrete triggering situation. There are no exclusions or named alternatives, but with only one sibling (verify_claim) that does something entirely different, no routing ambiguity exists.

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

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

Goes well beyond the annotations by disclosing the result shapes ('source' = ledger vs checker), automatic compound-claim splitting, receipt signing, and per-call billing. These details are consistent with readOnlyHint=false, idempotentHint=false, and openWorldHint=true — a non-idempotent, externally-billed call is exactly what the metering sentence describes.

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?

Front-loaded with the action and the return shape, then layered with cache, splitting, and billing details in descending priority. No sentence is redundant or restates the title.

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?

Despite having an output schema, the description still covers verdict vocabulary, confidence range, and the 'source' field, plus cost and caching semantics — everything an agent needs to decide whether to call and how to interpret the response.

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 coverage is 100%, so the `claim` parameter's format is already documented; the description adds real meaning by noting that a single `claim` value may contain a compound statement that gets split into individual facts. That is a usage-relevant behavior of the parameter not captured in the schema.

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 ('Submit one factual claim to ProofMart') and immediately enumerates the exact return payload (verdict enum, confidence 0-100, evidence, signed receipt). It is clearly distinguishable from the only sibling, list_plans, without opening either 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?

Gives strong contextual guidance: it discloses the metered cost model ('One call = one metered check') and explains the ledger-cache path so an agent knows a repeat check may be free and instant. It does not state explicit when-not-to-use conditions or name a sibling alternative, so it falls short of a 5.

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