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

With no annotations, the description carries the full burden, and it delivers: it explains optional Jev classification, error/off behavior, encrypted-content exclusion, the read-only nature ('Read source IDs and versions; no generated facts'), and the critical since_seq semantics. This is far beyond what the schema alone would tell an agent.

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?

Four sentences, each carrying distinct information: scope, ranking behavior, exclusions/read-only nature, and the key parameter caveat. The most important purpose is front-loaded and no sentence is redundant.

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?

The description plus schema is sufficient for an agent to invoke the tool correctly: required objective, optional scoping, connection credential guidance, and since_seq semantics are covered. The main gap is the lack of an explicit output/return format, though the description hints at what is returned ('source IDs and versions').

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 75%, so most parameters are already documented. The description adds essential nuance for since_seq, which the schema leaves undescribed, by warning that it is a message sequence and not the event cursor. This is meaningful because misusing since_seq would cause incorrect resumption behavior.

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?

The description names a specific verb ('Retrieve') and a specific resource ('bounded accessible message/page/request/task evidence'), and clarifies the purpose ('room resumption or objective'). It also differentiates the scope from single-type siblings like page_get, request_get, or messages_search by covering multiple evidence types at once.

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?

The context for use is clear: room resumption or objective-driven evidence retrieval. However, it does not explicitly name alternatives or state when not to use this tool versus siblings like task_context_list, messages_search, or page_get.

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