mark_as_read

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It partially satisfies this by documenting the return structure (marked_count, failed_count, details) in the Returns section, revealing idempotency hints (failed_count suggests partial success handling). However, it omits mutation semantics (permissions required, thread vs individual message behavior) that would be critical for a write operation.

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?

Uses a clean docstring structure with Args and Returns sections. Every sentence earns its place: the first line establishes the core operation and sibling distinction, Args documents the single parameter, and Returns documents the output structure. No redundancy or boilerplate.

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 single-parameter tool with zero schema coverage, the description adequately fills gaps by documenting the parameter (Args) and return values (Returns). Given the output schema exists (per context signals), the Returns section may be partially redundant, but still provides semantic field descriptions. Completeness is appropriate for the tool's simplicity.

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 description coverage is 0%, requiring the description to compensate. The Args section successfully defines 'message_ids' as 'List of message IDs to mark as read', adding essential semantic context (the IDs represent messages) and purpose (to mark as read) that the bare JSON schema lacks. It loses a point for not specifying ID format or constraints.

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 opening line 'Mark emails as read without archiving' provides a specific verb (Mark), resource (emails), and target state (as read). Crucially, it explicitly distinguishes itself from the 'archive' sibling tool by stating the negative constraint 'without archiving', preventing confusion between the two mutation operations.

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 phrase 'without archiving' implicitly provides usage guidance by contrasting with the sibling 'archive' tool, indicating when to use this (when you want to keep the email in the inbox but mark it read). While it lacks exhaustive when-to-use logic for all siblings (like search vs mark), it successfully handles the most critical adjacent alternative.

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