get_unread_digest

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

Discloses all key behaviors: read-only nature, no side effects on read status or search index, inclusion/exclusion criteria (denylist), output behavior (empty list vs missing data). Since annotations are absent, description fully covers transparency.

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?

Three sentences: one states purpose and output, second contrasts with alternatives, third clarifies behavioral constraints. Every sentence adds value, no 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?

Covers behavior, side effects, and edge cases (empty result). Lacks explicit output structure details, but since no output schema exists, the description provides enough for an agent to understand the returned data conceptually. Could mention that messages include text, timestamps, etc., but the key elements are described.

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?

Parameter descriptions in schema are already clear (limit for conversations to scan, perChat for messages per unread chat). Description reiterates default values but doesn't add new semantic details beyond confirming they are defaults. Schema coverage is 100%, so baseline 3 applies.

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?

Specific verb+resource: 'get unread digest' with clear scope: all conversations with unread messages, including decrypted messages and resolved names. Distinguishes from sibling tools list_conversations + get_chat_messages by being one-shot.

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: instead of combining list_conversations and get_chat_messages. Also clarifies limitations: denylist-excluded conversations omitted, returns empty list when nothing unread.

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