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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering safety. The description adds useful context beyond this: it reads from the local database (no network access) and describes the return fields, which is valuable for privacy and reliability expectations.

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?

The description is four short sentences, each adding distinct information: purpose, data source, return content, and usage hint. It is tight, front-loaded, and contains no filler or redundancy.

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?

With one optional parameter and an output schema present, the description covers all essential aspects: what it lists, where data comes from, what it returns, and how to use the result. There are no significant gaps given the tool's simple read-only nature.

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 has one optional parameter (limit) with complete description coverage (100%), including the default value of 50. The description does not need to repeat parameter details, and the schema fully communicates the only parameter, so a baseline of 3 is appropriate.

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 clearly states the tool 'Lists Signal conversations (chats) with last-active timestamps' and specifies the output includes chat IDs, contact names, and type. This distinguishes it from siblings like signal_read_messages (which reads messages) and signal_search_messages (which searches messages).

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 description explains the tool reads from the local Signal Desktop database with no network access, providing context for when it is appropriate. It also explicitly instructs to use the chat_id in subsequent signal_read_messages calls, implying a workflow and directing to the correct sibling tool.

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