Get Gmail Thread Content

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

Annotations already establish the safety profile (readOnlyHint, idempotentHint, non-destructive, openWorld), so the bar for the description is lower. The description adds meaningful behavioral context beyond annotations: the tool returns ALL messages in the thread, and the include_analysis flag flips the return shape from a formatted string to a structured dict containing last sender, ball-in-court verdict, per-sender counts, and participants. This explains behavior the annotations cannot convey and does not contradict them.

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?

Two sentences with zero waste: the first states the core function, the second explains the optional value-add and its benefit. The efficiency framing ('without re-parsing the formatted string or making a second tool call') earns its place by clarifying why the optional feature exists. Front-loaded, appropriately sized, no filler.

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?

With an output schema present, return-value documentation is handled elsewhere; annotations cover the read-only/idempotent profile; and the schema covers all parameters at 100%. The description is complete for the core task. The only meaningful gap is explicit routing to sibling alternatives (batch vs. single vs. message-level), which would round out the contextual picture but is not critical given the clear thread-scoped purpose.

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 100%, so the schema already documents all four parameters thoroughly, including defaults and enum semantics for body_format and include_analysis. Per the baseline rule, the description needn't repeat this. It adds marginal value by explaining the intent behind include_analysis ('who owes whom a response') but provides no additional meaning for thread_id, body_format, or user_google_email beyond what the schema already states.

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 opens with a specific verb+resource: 'Retrieves the complete content of a Gmail conversation thread, including all messages.' This clearly distinguishes it from siblings like get_gmail_message_content (single message) and search_gmail_messages (search), and the second sentence's ownership-analysis feature further differentiates it from get_gmail_threads_content_batch.

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 implies a use case — 'so a caller can determine who sent the last message and who owes whom a response... without making a second tool call' — which tells the agent when the optional analysis is valuable. However, it never explicitly addresses when NOT to use this tool or names alternatives (e.g., use get_gmail_threads_content_batch for multiple threads, get_gmail_message_content for one message). The guidance is implied, not stated.

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