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

Annotations only declare readOnlyHint=true; the description adds substantial context beyond that: what is never returned (full account numbers, raw keys, Vault secret ids), the Interactive Brokers analysis/backtesting exclusion, and the recovery actions (reconnect_broker, connect_broker) embedded in the result along with the precedence rule that an unrelated active account cannot suppress recovery. These are non-obvious behaviors an agent could not infer from the annotation.

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 tool's core purpose is front-loaded, but the body runs long for a two-optional-parameter read-only list call and repeats the no-secrets guarantee twice ('Raw credential values are never returned' and 'never includes full account numbers, raw keys, Vault secret ids'). The client-rendering and card-vs-Markdown-link passage is verbose and reads more like agent policy than tool definition, diluting the parts that matter for invoking this specific tool.

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, and the description compensates by enumerating the returned fields (broker, displayName, paperOrLive, accountDisplay, keyNames, status, timestamps, brokerDataExecution, recommendedForReadOnlyAnalysis) plus the connectionStatus/connectionUpdatedAt explainers and the structured recovery-action shape. An agent has everything needed to call this and interpret the response correctly.

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 carries the burden, and it does explain the intent split: brokerProvider for a named broker versus brokerCredentialId for one exact saved connection, with both acting as optional scoping filters on items and recovery actions. What it omits is any value/format guidance for brokerProvider (allowed broker names) and a reminder that the id is a UUID, which the schema only implies structurally.

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 opening sentence gives a specific verb and resource ('Lists saved broker credential metadata for the authenticated user') and immediately bounds the output ('Raw credential values are never returned'). It also separates itself from the sibling create_broker_credential by scoping that call to explicit user requests, so an agent can tell these apart without opening either schema.

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 states explicit selection rules: use recommendedForReadOnlyAnalysis=true for unnamed read-only requests, use another active item's id only when the user named it and it is not Interactive Brokers, call create_broker_credential only on an explicit create request. It also gives a clear prohibition ('Do not use a reconnect_required item for broker data, place_trade, or start_deployment'), which is exactly the when-not guidance the rubric rewards.

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