Read a thread

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

With no annotations, the description carries the full burden, and it does disclose real behavioral traits: the default truncation of quoted history, the full opt-in, and a prompt-injection warning that message content is untrusted. It omits auth requirements, rate limits, and pagination behavior for long threads, which keeps it below 5.

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 sentences, front-loaded with what the tool returns, then the default/override behavior, then the safety note. Every sentence earns its place and nothing is padded.

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 compensates by enumerating the returned fields and explaining the default-vs-full content difference. For a read tool of this shape it is nearly complete, though pagination or size limits for very long threads are unaddressed.

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 both parameters are already documented in the schema. The description's 'set full to get the whole text' largely restates the schema's own wording for full, adding little beyond the baseline.

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 ('Read one conversation') and enumerates exactly what comes back: sender, recipients, time, direction, verification status, and attachment names/sizes. The singular 'one conversation' cleanly separates it from the sibling list_threads.

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 gives clear operational context for the main choice an agent faces here — default (new text only) vs setting full — and the schema ties threadId to list_threads as the source. It does not name exclusions or alternatives (e.g., reply, mark_read) explicitly, so it stops short of a 5.

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