federation_assemble

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: verification is centralized on the SERVER (workers do not certify), divergence is preserved rather than best-of-N collapsing, model identity is retained, and a fallback path plus verdict values are given. It still omits auth/permission needs and side effects on session state.

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 compact and front-loads the verb, but reads as telegraphic fragments with heavy jargon (🔵, best-of-N, host_single_brain) crammed into one run-on block, which reduces legibility.

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 no-annotation, no-output-schema tool the description covers behavior, fallback, and verdict outcomes reasonably, but it leaves the sole input undocumented and does not clarify return shape beyond the verdict labels.

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 0% and the single required parameter (session_id) is never mentioned in the description, so the agent gets no semantics for the one input it must supply. The description's detail is entirely about behavior, not parameters.

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 concrete verb and resource ('Собрать совет' / assemble the council) and describes the operation's substance: grouping candidates by role, server-side citation verification, preserving divergence. It is distinguishable from siblings like seed_council or council_verdict, though it never names an alternative explicitly.

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 statement of when to use this tool versus the many federation_* and council_* siblings. The only conditional mentioned ('Пустая роль → host_single_brain') is an internal edge-case behavior, not guidance on tool selection.

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