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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, closed-world, so the safety profile is covered. The description adds genuine context beyond that: these snippets are never auto-sent and are meant for manual copy, which is a behavioral distinction no annotation conveys.

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?

Three short sentences, front-loaded with what the resource is before the exclusions. 'Text a human can copy when replying by hand' borders on redundant with the first sentence but does reinforce the manual-copy distinction.

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 zero-parameter, read-only list tool with full annotation coverage, the description is nearly sufficient. Since there is no output schema, a note about what each entry contains (e.g., title/body) would close the remaining gap, but nothing an agent needs in order to call it is missing.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the schema is trivially complete. Baseline 4 applies with no parameter semantics to elaborate.

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 defines the resource precisely (reusable human-copyable reply snippets kept by the team) and explicitly rules out two adjacent resource types, flow_get and agent_get. It relies on the title/name for the 'list' verb rather than stating it, but an agent can still tell exactly what data this returns versus its siblings.

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?

Negative routing is explicit — 'not sequence steps (flow_get), not agent FAQs (agent_get)' — which is exactly the discrimination needed among many *_list tools. It also clarifies the data is human-facing and 'nothing here is sent automatically,' implying a read/browse use case. It stops short of naming saved_reply_upsert as the write path.

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