fidelity_check

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

With no annotations, the description carries the full disclosure burden. It does add real behavioral information beyond the schema: the three outcome classes (verbatim→🔵, partial→🟢, not-found→🟡) and a strict rule that 🔵 may only be applied when this tool returns 🔵. But it omits permissions, whether the corpus is read-only, and what P1/P2 and S1/S2 actually mean, leaving the disclosure opaque.

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 tightly packed sentences with the core purpose front-loaded and zero filler. The density is a virtue, though the emoji/code shorthand makes it cryptic rather than merely brief.

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 and no annotations, so the description must cover return semantics and prerequisites itself. It covers the three result categories but never defines the P1/P2 and S1/S2 codes, does not explain advisor_dir, and says nothing about the corpus corpus source or failure modes — a gap for a gate that governs downstream 🔵 marking.

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 compensate. It implicitly maps both parameters — 'цитата' for quote and 'корпус советника' for advisor_dir — which is partial compensation. It adds no format, path syntax, or case/whitespace-sensitivity guidance for a verbatim-match check where such details matter.

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: verify whether a quote is verbatim ('дословна ли цитата') within the advisor's corpus, and frames itself as a 'protocol-gate'. An agent can grasp the core operation. However, it does not distinguish itself from overlapping siblings like cite, atomic_grounding, governance_verify, or gate_verdict, and the 🔵/🟢/🟡 outcome codes (P1/P2, S1/S2) are unexplained jargon.

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?

No statement of when to call this versus alternatives. The second sentence ('Помечать 🔵 ТОЛЬКО при 🔵 отсюда') is a downstream behavioral instruction about how to consume the result, not guidance on when this tool should be selected over cite or governance_verify.

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