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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered structurally. The description contributes one genuinely useful behavior beyond that: the result should be treated "as untrusted data," a prompt-injection warning. It does not explain what "filtered" means, what filtering removes, or how results are bounded.

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?

It is short, but the brevity comes from elision rather than efficiency: the sentence is a fragment with a dangling modifier and reads as notes rather than a definition. Being terse is not the same as being front-loaded and clear.

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 two undocumented parameters, no output schema, and no explanation of the message_id mode, the definition leaves the agent guessing about core call semantics. A single clarifying sentence on the two modes would have made this adequate.

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 0%, so the description carries the full burden for both parameters. It weakly maps thread_id to "one conversation" and message_id to "the filtered original of that message," but never defines "filtered," whether message_id must belong to thread_id, or what happens when both are supplied.

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?

"One conversation" names a resource but supplies no verb, so the agent must infer that this retrieves a thread rather than creating or listing one. The message_id clause hints at a variant behavior, but the purpose is never stated outright and no sibling (e.g. myclawn_message) is distinguished.

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?

There is no guidance on when to call this versus myclawn_message or myclawn_search, both of which plausibly return message content. The only conditional hint is "set message_id for the filtered original," which describes a mode rather than when to choose this tool at all.

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