collect_messages

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

With no annotations provided, the description fully discloses behavioral details: it fetches up to perChat messages, re-running repairs missing vectors, best-effort embedding, undecryptable messages skipped, and that a background loop usually handles updates. All relevant behaviors are explicitly stated.

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 well-structured and front-loaded with the main purpose. It contains all necessary information but is slightly longer than necessary. Still, every sentence adds value and it remains coherent.

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?

While the description explains behavior well, it does not mention what the agent can expect as output or return value, and there is no output schema. For a tool that fetches data, stating the outcome or structure would improve completeness.

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 provides 100% coverage with descriptions for both parameters (chatIds and perChat). The description adds meaningful context: chatIds are MIDs from list_conversations, perChat defaults to 100, and omitting chatIds collects from all conversations. This goes beyond the schema alone.

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 bulk-fetches recent LINE messages into a local search index, distinguishing it from siblings like get_chat_messages and search_messages. It uses specific verbs ('bulk-fetch', 'repairs') and names the resource ('LINE conversations', 'Yomi's local cross-conversation search index').

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?

Explicitly states when to use: 'only to force a reconcile or backfill specific chats', and notes that normal updates are handled by a background loop, so this tool should not be used for routine updates. This provides clear guidance on alternatives.

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