cached

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

No annotations are present, so the description carries the full behavioral burden. It does not state whether the local mirror can be stale or when it syncs (though 'sync' is a sibling), nor return shape, failure modes, or whether it requires an established session (login is a sibling). For a read tool with zero annotations and no output schema, this is a notable gap.

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?

A single concise clause that front-loads the action and target ('Read cached messages of a chat') before the source ('from the local mirror'). No filler.

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?

For a no-param read with no annotations or output schema, the definition is only just sufficient. It omits the one thing an agent needs most: how this differs from 'messages' and what the local mirror's freshness/availability guarantees are.

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?

Zero parameters and four is the baseline. No parameter semantics are needed, and the description introduces no confusing parameter claims.

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 (cached messages of a chat) and adds the qualifier 'from the local mirror', which signal a distinct read path. It is largely self-explanatory but does not explicitly contrast with the sibling 'messages', which appears to be the live counterpart, so it falls short of an unambiguous 5.

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?

No explicit guidance on when to use this tool instead of the sibling 'messages' or 'read'. The phrase 'local mirror' implies an offline/cached read, but the agent is left to infer the scenario without any stated condition or alternative.

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