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 the returned field set and the backing endpoint (GET /api/v1/topics), which is genuine added context, but it says nothing about volume, pagination, or whether disabled topics are included alongside active ones.

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 the purpose, then the use case, then the API mapping. Nothing is redundant and nothing needs to be re-read.

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 parameters and no output schema, the description carries the burden of describing the return shape, and it does list the four fields. It leaves open whether results are paginated or include disabled topics, which is the only meaningful remaining gap for such a simple tool.

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 the baseline is 4. The description's parenthetical is about response fields rather than inputs, and it correctly conveys that no filtering arguments exist.

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?

Specific verb plus resource ("List the conversation topics") and it enumerates the returned fields (id, name, parentId, disabled), which no sibling list tool covers. An agent can immediately tell this apart from gladly_list_inboxes or gladly_list_audiences.

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?

Gives a concrete trigger: "Use it to turn the topicIds of a conversation into names," which tells the agent exactly when to call it. There are no competing siblings to exclude and no explicit when-not, so it stops just short of a 5.

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