Conformance oracle

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

With no annotations, the description carries the full behavioral burden, and it discloses only commercial traits (cost tier: $4.99 / trial / pass) and the fact that a verdict is "signed". It says nothing about side effects on the target server, authorization needs, runtime duration, or whether the probe is non-destructive — all critical for a tool that takes a server_url and runs scenarios against it.

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?

It is a single compact sentence with no filler, so nothing is wasted, but the terseness comes at the cost of comprehension — the jargon-heavy phrasing reads like a marketing label rather than an instruction. Front-loading is acceptable, but brevity here is under-specification rather than efficient structure.

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 complex, five-parameter tool with no annotations, no output schema, and no parameter documentation, the description is far too thin. It omits what the tool returns (beyond "signed verdict"), how parameters are used, and how it relates to verdict_query, leaving an agent unable to invoke it reliably.

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?

Five parameters exist at 0% schema description coverage, and the description explains none of them. "A2A fold" loosely gestures at a2a_base_url, but required fields like server_id, server_rev, and server_url are left entirely undefined in both schema and description. The description does not compensate for the coverage gap.

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 operation ("Full pair check") and enumerates components (census + claim-triggered scenarios + A2A fold, signed verdict), so an agent gets a rough sense of what is produced. However, it is saturated with internal jargon ("A2A fold", "claim-triggered scenarios") that is never explained, and it does nothing to distinguish the tool from its sibling verdict_query. The purpose is recognizable but vague.

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?

There is no indication of when to use this tool versus verdict_query, nor of prerequisites, scope, or conditions. The only hint of context is the pricing/tier fragment ("$4.99 / trial / pass"), which implies a paid trial but doesn't tell the agent when this probe is appropriate. No usage guidance is provided.

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?

With no annotations, the description carries the full behavioral burden; it does disclose two non-obvious traits: a per-call cost and invalidation on any version change. It omits what a caller actually receives (verdict payload shape), what happens on a miss/expiry (error vs. empty), and any auth or rate-limit constraints, so it remains materially incomplete for a zero-annotation tool.

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?

A single dense sentence that front-loads the purpose, then the cost, then the invalidation rule, with no filler. It is terse to the point of being cryptic, but every clause earns its place.

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?

No output schema, no annotations, three undocumented required parameters, and a sibling tool that is never referenced. The description never explains what a 'verdict' contains or how expiry surfaces to the caller, so an agent lacks enough to invoke and interpret it confidently.

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% and the description names none of server_id, client_rev, or server_rev, so no parameter meaning is added. Worse, 'exact pair' implies two identifiers while the schema requires three, which could mislead an agent about the key structure.

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 a specific verb and resource ('query' a 'stored signed verdict') and qualifies the scope ('for an exact pair'), so an agent knows it is a cache-lookup tool rather than a computation. It does not, however, name or distinguish itself from the sibling conformance_probe, and 'exact pair' is ambiguous given three required params.

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?

Cost ('$0.01 / pass') and the expiry rule ('EXPIRED on any version move') imply when the call is worthwhile versus re-deriving a verdict, which is useful implied guidance. There is no explicit when-to-use/when-not statement and no mention of conformance_probe as the alternative when a version has moved.

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