search_messages_by_heard_status

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful context beyond annotations: the return shape, the unheard_counts_by_channel aggregation, and the warning that the full payload is much larger, prompting the NARROW guidance. No contradiction with annotations.

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 front-loaded with purpose, then uses clear labeled sections (USE WHEN, USE INSTEAD, EXAMPLE, RETURNS, NARROW). Every section earns its place and the format aids scanning. Length is justified by the tool's complexity, with no redundant sentences.

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?

For a 7-parameter tool with no output schema, the description covers the key gaps: usage context, alternatives, response shape, and payload optimization. The one limitation (no date filter) is disclosed. It stops short of describing pagination or interaction with limit, but the schema already documents limit's range and default, so the combination is adequate.

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 coverage is 100%, so parameters are already fully documented. The description adds real value by recommending a specific response_fields dot-path allowlist, demonstrating with an example how to shrink the payload. It also reinforces that heardStatus='unheard' is the unread filter. This goes beyond mere schema repetition.

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 and resource ('Find messages by whether you have listened to them') plus a distinct capability not implied by the name: per-conversation unheard counts. It differentiates from siblings by naming search_message_ids and list_messages as alternatives. The purpose is unambiguous and actionable.

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 USE WHEN section explicitly frames the intended scenario ('What have I not listened to yet' / 'catch me up') and flags the unread filter. USE INSTEAD names exact alternatives (search_message_ids for notified state/mentions/date anchors; list_messages for plain history) and discloses a key limitation: no date filter. This is exemplary when/when-not guidance.

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