sage_message_history

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

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly states the tool is non-mutating ('without claiming, acknowledging, or re-queueing'), explains the durability difference between canonical messages and deprecated pipe rows, and warns that payloads and replies are untrusted. This is substantial transparency, though it does not mention pagination or sorting behavior.

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 three sentences long, front-loaded with the main action and purpose. It is concise while including necessary caveats about durability and untrusted data. The structure is logical, though the final sentence about untrusted data could be seen as extra 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?

The description covers the tool's primary use cases (browsing inbox and outbox), its non-mutating nature, the distinction between canonical and transient messages, and a security note about untrusted data. For a read-only browse tool with a simple schema and no output schema, this is fairly complete, though it does not describe the return format or ordering of results.

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 already provides descriptions for both parameters (100% coverage), so the baseline is 3. The description adds semantic value by explaining the behavioral difference between folder='inbox' (reopen after claimed/completed) and folder='outbox' (revisit sent messages), going beyond the schema's generic 'History to browse'.

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's purpose: 'Browse your retained message inbox or outbox' with specific verbs and resources. It distinguishes from siblings by emphasizing it does so 'without claiming, acknowledging, or re-queueing a message,' which is a unique capability compared to tools like sage_inbox or sage_message_reply.

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 provides explicit usage context, including when to use folder='inbox' to reopen claimed/completed messages and folder='outbox' to revisit sent messages and workflow state. It implies when not to use (i.e., not for claiming/acknowledging), though it does not name alternative tools directly.

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