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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description has less to prove. It still adds useful traits: results are newest first, scope is limited to org admins, source systems are the Simple page and the portal, and it is a 'Read tier' call. Nothing is said about pagination.

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?

One dense sentence plus a short tag sentence. The endpoint, ordering, both modes, parameter roles, scope, and tier are all front-loaded with no filler.

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, but the description says a single-thread read returns the thread with its messages, and it covers the list mode's ordering and scope. Only the pagination or limit behavior and the result shape of the list mode are left implicit.

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 description coverage is 0%, so the description must explain all three parameters, and it explains admin_id and thread_id well. limit is never mentioned, however, so the agent must infer its meaning and default from the name alone.

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 and resource ('List the Ask TaScan chat threads') and covers both modes: listing org admin threads or reading a single thread with its messages. This separates it cleanly from siblings like tascan_delete_chat_thread and tascan_save_chat_thread.

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 description tells the agent which parameter selects which mode: admin_id narrows to one admin, thread_id switches to reading a single thread with messages. It implies the default (list across admins) but gives no explicit exclusion or fallback tool for cases this can't serve.

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