get_thread

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

Goes well beyond readOnlyHint/openWorldHint: it discloses a content transformation (quoted history is trimmed so each message shows only what it added) and that results are wrapped in an UNTRUSTED block with an explicit instruction not to follow embedded instructions. That is the security-relevant behavior an agent needs to handle output safely.

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 short sentences, zero filler: capability and input forms first, then the trimming behavior, then the safety framing. Each sentence carries distinct, actionable information.

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 no output schema, the description still conveys the result shape that matters: ordering (oldest first), content normalization (trimmed quotes), and the UNTRUSTED wrapper. For a two-parameter read tool this covers everything needed to call and interpret it correctly.

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 the baseline is 3; the description adds only mild reinforcement that thread_id can be any message ID in the thread, which largely restates the schema's 'Thread ID or message ID'.

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 ('reads'), a specific resource ('a whole conversation'), the ordering ('oldest first'), and the acceptable identifiers. Saying 'whole conversation' implicitly but clearly separates it from the single-message siblings (get_email) and from search tools.

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?

It explains which ID forms are accepted ('thread ID or by the ID of any email in it'), which is real usage guidance for choosing inputs. However, it never states when to prefer this over get_email or search_emails, nor any exclusions or prerequisites, so the when-to-use decision is only implied by the resource noun.

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