research_critic

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

No annotations are present, so the description carries the full burden. It explicitly discloses non-mutating behavior ('отчёт НЕ правит — только флагает'), a hard prerequisite (DEEPSEEK_API_KEY or OLLAMA_HOST), the failure mode ('недоступен'), and the output classification labels. This is substantial behavioral context beyond a bare verb.

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 core behavior is front-loaded and most sentences carry operational value. However, the sentence about '11-57% ошибок цитирования у коммерческих агентов — мы меряем СВОИ' is promotional noise that does not help an agent call the tool, and the 'канон groundwork/DCM 2026' phrase is opaque jargon.

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 tool with one parameter and an existing output schema, the description covers the main behavior, result categories, environment requirements, and non-mutation constraint. It lacks a precise definition of camp_id and an explicit when-to-use statement, but an agent can still determine how to invoke it and what to expect.

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 does not compensate. The only parameter, camp_id, is only indirectly tied to 'отчёт кампании'; its format, origin, required type beyond string, and how to obtain a valid value are unaddressed. The parameter name is mildly self-explanatory but the description adds no real semantic detail.

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 'КРИТИК-РЕВЬЮЕР' and a concrete pipeline: campaign report → extract 3-5 key claims → verify each against source texts → classify as supported/unsupported/unverifiable. This identifies a specific action and resource, and clearly differentiates it from sibling research_* tools that generate reports or track status.

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?

The description implies use for post-hoc fact-checking of an existing campaign report, and states it does not correct the report, only flags. However, it never explicitly names alternatives or gives conditions for choosing this tool over, say, research_report or research_status.

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