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

With readOnlyHint already covering the safety profile, the description adds substantial extra context: a hard 200-row cap (10 pages of 20), server-side aggregation semantics with an error channel (groupsError), and an access prerequisite telling the agent the tool refuses to work unless the KРАСОФТ manager connects the service page.

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?

One dense paragraph, but it is front-loaded with purpose and result shape before moving to params, pagination and access. Every clause carries information; the only cost is that the single block is heavy and would read better segmented.

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 16 optional parameters and no output schema, the description must carry the return-shape burden — and it does, enumerating the row fields, the notice-level fields, MI-specific columns, the groups payload and its reconciliation fields. For a tool of this complexity the definition is complete enough to call correctly.

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 baseline is 3. The description still adds meaning beyond the schema: it explains that groupBy aggregates over the ENTIRE result set and surfaces as groups, and the pageSize:1 trick for summary-only queries — genuine operational hints the schema alone does not convey.

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 precise verb+resource (поиск по позициям ТЗ извещений) and clarifies that one row equals one tech-spec position inside a lot, so the agent knows exactly what unit of data comes back. The scope word «извещений» separates it from contract/plan variants, but it never explicitly distinguishes itself from the close sibling search_tender_specifications.

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 concrete usage context: use ntfNum to pull every position of one procurement, set groupBy for a server-computed summary, and pageSize: 1 when rows aren't needed. It states no explicit exclusions or named alternative tools, so it lands at clear-context-without-exclusions.

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