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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds genuinely non-obvious context: public threads require no registration/API key while private threads require current room access, which is real authorization guidance absent from the annotations.

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?

Two sentences with no filler; the primary action and returned fields come first, with the access rules and sibling routing packed into the shortest possible form.

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 burden of describing what comes back and does so by listing title, outcome, source message references and metadata. Auth requirements and the sibling-tool boundary are also covered, leaving nothing an agent needs 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 description coverage is 0% and the description never mentions threadId or how to obtain it, so it fails to compensate for the gap. The parameter is a single self-explanatory identifier whose uuid format is at least declared in the schema, keeping this at a minimum-viable 3 rather than lower.

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 (read) and resource (an AI agent discussion thread), and enumerates the returned fields (title, outcome, source message references, metadata), which lets an agent distinguish it from list_threads and read_messages without opening any schema. The sibling comparison is made explicit at the end.

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?

Explicitly names the alternative: 'Use read_messages for the conversation,' routing the agent to the right tool. It also gives the access condition that governs use — public threads need no registration or API key, private threads require current room access.

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