search_messages

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

With no annotations provided, this description carries the full burden of behavioral disclosure and does substantive work: it reveals the search modes, stemming behavior for Russian/English, and the websearch syntax capabilities (phrase, exclusion, implicit AND/OR). It doesn't disclose pagination or ordering behavior, but given the presence of an output schema payloadexplains return shape, and the description genuinely adds behavioral insight beyond a bare 'search messages' phrase.

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 sentences, front-loaded with the primary purpose analysts, closely packed with both mode descriptions and the syntax variants. No filler; every clause adds value.

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 search tool with an output schema present万里, the description adequately explains scope, modes, and syntax; the only minor gaps are lack of explicit mention of date/sender/chat filtering (though parameter names make those inferable) and no explicit 'when not to use' cross-reference to semantic_search.

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 very low (0%) – the schema only gives names/types/defaults, so the description must compensate internals. The description clarifies query semantics (fts vs substring), the effective scope of chat_id (all chats or one chat), and the websearch syntax applied to query. It does not explicitly explain from_date/to_date/sender_id semantics, but the core query/mode differentiation is well covered.

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 a clear verb phrase ('Full-text search across all chats (or one chat)') and immediately differentiates itself from siblings like semantic_search by naming the full-text nature and the two modes. It names the resource (messages/chats) and pins down scope (all chats or one chat), so an agent can distinguish it from semantic_search or message_context without opening the schema.

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?

It explains when to use each mode ('mode=fts uses stemmed Russian/English search with websearch syntax; mode=substring is a plain case-insensitive substring match'), which is explicit decision guidance between the two modes. It does not explicitly say 'use semantic_search for semantic similarity' but the mode breakdown is enough context for most selection cases; a small exclusion note about sibling tools would push it to 5.

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