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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds ordering (oldest first) and message attribution context, which is useful, but doesn't address pagination behavior or limits despite a limit parameter existing.

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 efficient sentences: the first states core behavior, the second adds procedural guidance. No redundant or filler content.

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?

Covers the essential read purpose and ordering, but doesn't mention pagination or the limit parameter, which is relevant for a conversation with many messages. With no output schema, a brief note on return shape (e.g., message list with timestamps) would strengthen it.

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 description coverage is only 33%; conversation_id references highlevel_conversations and location_id/limit are undocumented. The description doesn't clarify the limit parameter or its range/default, leaving a gap. Baseline 3 applies given partial schema coverage.

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 specific verb+resource: read messages in one conversation, with ordering (oldest first) and message attribution ('customer' or 'you'). This clearly distinguishes it from siblings like highlevel_conversations (list) and highlevel_send_message (write).

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?

Provides clear context: 'Read the thread before replying — never answer a customer without seeing what they actually asked.' This gives a usage condition tied to highlevel_send_message, but doesn't name the alternative tool explicitly or describe when not to use it.

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