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

Annotations already cover safety (readOnly, idempotent, non-destructive), but the description adds real behavioral context: newest-first ordering, the three fields each conversation carries, and the fact that phone numbers are masked when the case is configured that way. That masking rule is not available anywhere in the structured fields.

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 tool returns, then the filter, then the masking caveat. No filler, though the third sentence is a niche edge case that could be folded in.

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?

There is no output schema, so the description carries the return-value burden itself and does so by listing the fields and their ordering plus the masking behavior. For a two-parameter read-only list tool, nothing essential 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?

Schema coverage is 100%, so the schema already documents both parameters including bounds and defaults. The description restates alleen_terugbellen as 'open terugbelverzoeken', which matches the schema wording and adds no new meaning, and it never mentions limiet.

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 the resource (recent conversations of the AI telephonist), the ordering (newest first), and the fields returned (subject, summary, callback status). This clearly separates it from sibling tools such as crm_afspraken or crm_contacten.

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 only usage guidance is the conditional filter sentence about alleen_terugbellen. There is no explicit statement of when to prefer this tool over other lookup tools like crm_zoek or crm_open_taken, so when-to-use is only implied.

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