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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds substantial context beyond them: the required api:account scope, that revocation happens at SnapTrade while other links survive, that the action is irreversible and requires re-login, and that it never sells or moves holdings.

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-loads the action, then layers in the precondition, parameter behavior, irreversibility, and safety reassurance. Every sentence carries distinct information 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?

For a destructive mutation tool this is complete: permission requirement, confirmation precondition, per-parameter effects, irreversibility, recovery path, absence of trade side effects, and return value are all covered.

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 the schema documents both parameters, but the description adds relational meaning: connection_id revokes one link 'and keeps the others' while all:true also removes the SnapTrade registration. This is value beyond the bare schema text.

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 (disconnect/unlink) and resource (brokerage), scoped to 'YOUR Gambit account', and is clearly distinguishable from siblings like start_brokerage_connect and list_brokerages which it names.

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?

Gives explicit when-to-use ('Call it ONLY when the user explicitly asks to unlink, and confirm which one first') and points to the alternative path for restoring access (start_brokerage_connect). Both the trigger condition and the recovery route are stated.

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