config_set

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

With no annotations, the description carries the full burden and does add useful context: the atomic save behavior to v8help.toml and the set of valid keys with value domains. But for a mutation tool it fails to disclose whether unspecified settings are preserved or reset, whether a rebuild is required for changes to take effect, or what validation/error behavior occurs on invalid keys.

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 with the action front-loaded ('Изменить настройки и сохранить в v8help.toml (атомарно)') followed by the key enumeration. The key list is long but earns its place since the schema does not enumerate valid keys. It could be better organized, but there is no wasted text.

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 no annotations and no output schema, the description covers the what and where well but omits post-invocation behavior: return value, whether a rebuild is needed after configuration changes, and whether values are merged into or replace the existing config. The nested embedder.index/query structure also hints at depth the flat-keys contract does not clarify. Adequate for basic invocation, with clear gaps.

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?

The schema only says 'Плоские ключи -> значения' (flat keys -> values) with 100% coverage, so the description adds real value by enumerating the valid keys and their value types — search.backend options, embedder.index/query sub-keys, bin_dir, lang, books. This exceeds the schema baseline of 3, though it stops short of specifying exact types for every key.

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 ('Изменить' — change), a precise resource (settings), and the persistence target (v8help.toml) with atomic-write semantics. The enumeration of valid keys and value domains (fts|hybrid|vectors) defines the exact scope, making it clearly distinguishable from the sibling config_get (its read counterpart).

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 verb 'Изменить' implies this is the write tool and config_get is the read tool, and the key list tells the agent what can be modified. However, the description never explicitly says when to use this tool versus alternatives — no mention that reading settings should route to config_get, and no exclusions or conditions are given.

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