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

Annotations already claim readOnlyHint=false, idempotentHint=true, and destructiveHint=false, but the description's claim that 'pending requests ended... and nothing was shared' reads as though nothing happens, leaving the agent unsure whether the call mutates state. It says nothing about the user_confirmed confirmation gate, what happens on repeat calls despite the idempotency hint, or why a mutation is safe.

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?

It is short (three sentences), but the lead sentence is a retention date rather than the tool's action, so the most important information is not front-loaded. The final two sentences are unrelated commercial boilerplate about lawyer payment and ranking that consume space without aiding selection.

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?

An output schema exists, so return values need not be explained, but for a non-read-only tool with a mandatory in-conversation user confirmation this description omits the entire confirmation flow and its state-changing impact. An agent reading only this text would not know whether calling it is safe, necessary, or a no-op.

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?

With only 40% schema description coverage across 5 parameters, the description must compensate, yet it mentions no parameter at all. referral_id, opposing_party_name, and intake_notice_acknowledged carry no explanation in either the schema or the description, and the required user_confirmed gate is only explained in the schema.

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 text is framed as a retention/deprecation notice ('Kept until 2026-12-15 so older connections get a plain answer') rather than stating what confirm_introduction does when invoked. It never says whether the call is a no-op stub, a status acknowledgement, or an actual confirmation action, so the agent cannot determine the tool's function from the description alone.

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?

It explicitly routes to alternatives ('Use preview_client_message, then send_client_message'), which is genuinely useful, but it never states the condition under which this tool should still be called (e.g. requests created before 2026-11-04) versus skipped entirely. The 'listing service, not a lawyer referral service' sentence is unrelated to invocation choice.

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