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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety is covered; the description adds real context beyond them — that answer rendering is in-chat, that citation labels come from the backend and must not be invented, and that pending jobs are viewable. It does not cover failure behavior for an expired/unknown job_id, which is the main gap.

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?

Front-loaded with the core action, then routing, then parameter notes — a sensible order with no filler sentences. Slightly dense, and the trailing 'Preserves backend citation labels; never invent sources' is prompt-style guidance that sits a bit awkwardly on a read tool, but it is short.

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 viewer with an output schema, remaining needs are modest: the description covers sequencing, the required id pair, and the reference_label mode, so an agent can call it correctly. What it omits is what happens when the job is not present or the ids mismatch, and it never ties organization_id to the billing/membership choice documented only in the schema.

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 only 25% (only organization_id carries a description), so the description must compensate — and it does for three of four params: session_id and job_id are framed as the pair to retain for follow-ups, and reference_label is explained as selecting one cited quotation with its transcript/recording context, which the bare regex pattern does not convey. organization_id is left to 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?

Specific verb+resource: 'Show the full answer in this MCP chat with clickable verified quotes and original recordings' tells an agent exactly what is produced, and it is clearly differentiated from the queue/chat siblings (chat_research_session, queue_research_chat) it names. The note that pending jobs can be checked here further delimits the resource from a pure read of a finished answer.

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?

Explicit sequencing ('Use after chat_research_session or queue_research_chat'), an explicit exclusion ('never substitute an external dashboard link'), and a conditional mode ('Set reference_label to read one cited quotation'). It also tells the agent to retain session_id/job_id for follow-ups, which is actionable routing guidance rather than inference.

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