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

Annotations already declare readOnly/non-destructive/open-world, and the description adds genuinely useful context beyond them: page size (up to 50 conversations) and an authentication prerequisite (Cotlet API key with access to the app). It does not mention ordering, cursor/pagination behavior, or rate limits, so it is not exhaustive.

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?

The first two sentences say essentially the same thing ("inbox conversations with the latest messages, across email, text and other connected channels"), so a full sentence is wasted on restating the name/title. The remaining sentences are tight and front-load the useful facts.

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 read-only list tool with no output schema and only two well-documented params, the description covers what is returned, filtering, page capacity and auth requirements. It leaves sorting/ordering and cross-page behavior unspecified, which keeps it short of complete.

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 3 is the floor, but the description adds meaning to both params: client_id narrows to a single thread, and "pages hold up to 50" clarifies the limit range in schema terms. The limit/"page" terminology is slightly ambiguous about whether paging is automatic.

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 (Lists) and resource (inbox conversations with the latest messages) and scopes it to email, text and connected channels, so the agent knows exactly what it returns. It does not differentiate itself from sibling conversation/message tools (e.g. thryv_send_message), and the opening sentence largely restates the second, so it stops short of a 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?

"Filter by client to see one thread" implies when to pass client_id, which is a usable hint. There is no explicit when-to-use vs. alternatives guidance and no exclusions, so usage remains implied rather than stated.

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