get_capability_snapshot

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

No annotations are supplied, so the description carries the full disclosure burden. It does well on several points: free/no-cost, read-safe by nature, returns only keys and nesting and 'never values' (data exposure profile), and the >=0.95 healthy threshold for the shape score. It omits failure behavior for an unknown slug, whether an agent with zero paid calls returns an error or an empty structure, and any bounds on n.

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 output contract is front-loaded, which is good, but the text is padded with promotional framing — '[FREE]' in the opening tag and a redundant 'Free.' closing line say the same thing twice. 'Public evidence, not a marketing claim' is positioning copy rather than operational information. Tightening the bracketed price tag and the closing sentence would not lose any instruction.

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 output schema and no annotations, the description does the heavy lifting well: it names the three returned elements (top observed JSON paths, advertised-shape match score with its threshold, latest settlement tx) and the keying convention. What remains thin is edge-case completeness — unknown slug, agents with no paid history, and the valid range for n.

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% for both parameters, so the description must compensate. It adds real meaning for 'slug' by enumerating valid values (forge, cipher, duke, gridiron, wally, odds, scout and other AgentPayStore agents), which no schema field provides. It adds only partial meaning for 'n' — 'last N paid x402 calls' ties it to the sample window but never states a maximum, minimum, or what happens beyond the default of 20.

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 names a specific verb and resource: it returns the observed response structure of the last N paid x402 calls for an agent, keyed by settlement tx, plus an advertised-shape match score. That is far more precise than a name restatement and it clearly distinguishes itself from generic trust/profile siblings. It stops short of a 5 because it never names the nearest alternative (e.g. get_agent_trust_pulse or check_x402_endpoint), leaving overlap resolution 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?

Explicit timing guidance is given: 'Check BEFORE paying', framed as pre-purchase due diligence on an agent. It also clarifies this is free and that the evidence is observed rather than advertised. It does not state when NOT to use it or which sibling tool covers adjacent questions, so it sits below the 5 tier.

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