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

Annotations only declare readOnlyHint: false, so the description carries the burden. It fully discloses that the token is validated against Mercury's accounts endpoint, stored only if valid, that access is READ-only (balances/transactions), that the token is sensitive and vault-encrypted, and never returned/logged/echoed. This goes far beyond the annotation and gives the agent a precise safety profile.

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 description is dense but every sentence earns its place: purpose, authentication method, validation flow, access scope, security, and optional parameter. It is front-loaded with the core function and then layers details, making it easy for an agent to parse quickly.

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 security-sensitive setup tool with four parameters, the description covers all operational aspects: validation, storage, access limits, token handling, and optional webhook. An output schema exists (indicated), so return values are presumably documented elsewhere. Nothing an agent needs to call this tool correctly is missing.

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%, and the description adds meaning beyond each property's schema description. It explains org_id defaults to the key's org and never needs to be asked, actor_id defaults to the org entity and arbitrary UUIDs are rejected, api_token is sensitive and never logged, and webhook_secret enables live events. This enriches the schema without redundancy.

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 description states a specific action (connects org to Mercury) with a specific mechanism (API token, not OAuth), and clearly distinguishes from siblings like connect_meow and disconnect_mercury by naming the integration target. It leaves no ambiguity about what the tool does.

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 explains the authentication method (token, no redirect), the validation-and-store flow, and the optional webhook secret use case. It also notes the token is read-only, which implicitly tells the agent this is for setup, not for moving money. The distinction from connect_meow (another integration) is clear via context, and disconnect_mercury is the obvious inverse.

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