get_thread

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

The description adds behavior beyond the annotations ('readOnlyHint: true, destructiveHint: false') by explicitly stating 'Does NOT mark emails as seen.' This is useful because many email tools inadvertently mark messages as read. It also discloses how maxLength truncates bodies ('A hint shows how many characters remain') and how newestFirst changes the response structure, giving the agent expectations about output 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 composed of four concise sentences that each earn their place: the core purpose, a key side-effect (not marking as seen), format guidance, newestFirst guidance, and a prerequisite. It is front-loaded with the most important information and tightly scoped with no filler or repetition.

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 tool has 6 parameters and no output schema, but the description covers the return concept ('Returns all related messages') and explains key options (format, newestFirst, maxLength). It also references the required prerequisite (get_email). It does not describe response fields or ordering details beyond newestFirst, but for a read-only thread reconstruction tool, this is adequate context given the rich input schema.

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 detailed descriptions for all six parameters (100% coverage), so the description's input-schema value is marginal. The description does add workflow context like 'from get_email' for message_id and 'Ideal for AI triage' for newestFirst, but these are usage hints rather than semantic explanations of parameter values. Per calibration, a baseline of 3 is appropriate when the schema carries the parameter documentation burden.

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 'Reconstruct a full email conversation thread by following References and In-Reply-To headers' – a specific verb and resource that clearly distinguishes it from siblings like get_email (single message) and get_emails (likely bulk). It also explicitly states the tool's output: 'Returns all related messages.' This is unambiguous and action-oriented.

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 clear usage context, including a prerequisite ('Use get_email first to obtain the message_id') and specific guidance for parameters (`Use format="text" to strip HTML, or format="stripped" to also remove quoted replies`, `Use newestFirst=true to show the most recent message in full`). It also states an ideal use case ('Ideal for AI triage of long threads'), but it does not explicitly say when not to use this tool versus alternatives beyond the get_email prerequisite.

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