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

Beyond the readOnlyHint and destructiveHint annotations, the description reveals that historical backfill is impossible, that results are limited to the linked/listening capture window, and that a missing Zalo connection yields an actionable connect hint rather than a generic error. This is substantive behavioral context, not a restatement of annotations.

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-load the core purpose and then add the two most decision-relevant constraints. There is no filler, repetition, or unnecessary detail.

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 simple two-parameter read-only search tool, the description covers data availability, connectivity requirements, and failure behavior. The absence of an output schema is mitigated by the clear search semantics and the schema's documented limit parameter.

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 input schema already documents both parameters with 100% coverage, so the baseline is 3. The description adds only the general notion of text search and capture scope, which does not materially extend the schema's documentation of query and limit.

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 specific verb and resource: 'Searches your captured Zalo messages by text.' It further delimits the scope to messages captured while Local MCP was linked and listening, which clearly separates it from zalo_read_messages and platform-specific search siblings.

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 gives a concrete prerequisite ('Requires Zalo linked') and a clear exclusion: only messages captured while Local MCP was linked and listening, because Zalo can't backfill older history. This tells an agent when the tool can succeed and what to expect otherwise, though it does not explicitly name sibling alternatives like signal_search_messages or whatsapp_search_messages.

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