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

Goes well past the readOnly annotation to disclose non-obvious traits: reading does not mark the chat read, deleted messages have no body, agent-authored messages omit author, and secret chats return empty bodies and cannot be written to. These are exactly the surprises an agent must know.

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?

One dense paragraph with paging logic front-loaded, and every sentence carries new information. It is on the long side with stacked parentheticals, which costs a little readability but not substance.

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 carries the full burden and delivers: it enumerates the message fields (author/agent, body, deleted, replyTo, files, issues) and the 'working' list, so an agent knows what it will get back.

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 already 100%, so the baseline is 3; the description adds operational meaning by explaining the before/after cursor idiom and the feedback loop via 'more', which goes beyond the terse schema strings. The 'limit' parameter is left to the schema.

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 ('A chat's messages') plus the ordering and cursor scope, so an agent immediately knows this is the message-reading tool for a single chat, distinct from list_chats or send_chat_message.

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?

Explains how to page ('before' reads back, 'after' reads forward, 'more' means pass the first message's id) and names mark_chat_read as the tool that actually marks a chat read. It lacks explicit when-not-to-use conditions, but the operational context is clear.

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