read_conversation

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

With no annotations, the description carries the full burden and does so: it declares this is non-mutating ('Marks nothing read'), discloses ordering and pagination behavior, explains how broadcasts are represented as the recipient's copy, and spells out the removed-agent name edge cases. These are non-obvious behaviors an agent could not infer from the schema.

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?

Front-loaded with the core action and paging rule, and every clause adds real information. However, the long semicolon-chained single sentence plus the dense removed-agent caveat makes it harder to scan than it needs to be.

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?

No output schema exists, and the description compensates by enumerating the returned fields (id, inReplyTo, from, to, sentAt, body, broadcast) and their meanings. Combined with the pagination contract, prerequisite, and edge-case handling, an agent has everything needed to call 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 only 33% (only 'name' is documented there), so the description must compensate and does: it explains limit's default 50 and cap 200 and defines offset's paging role via 'call again with a higher offset'. The name parameter's meaning is also reinforced as 'one agent or person', matching the schema's case-insensitivity note.

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 your direct messages with one agent or person') and immediately scopes it to a two-party exchange, which distinguishes it from read_inbox, search, and read_channel. The parenthetical 'those they sent you and those you sent them' removes any ambiguity about directionality.

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?

Gives concrete operational guidance: newest first, one page at a time, 'a full page means there may be more, so call again with a higher offset', and the prerequisite 'Requires register first'. It does not explicitly say when to prefer this over read_inbox or search, so it stops short of full routing guidance.

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