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

Annotations already declare readOnly/idempotent, and the description adds substantial behavioral context: caveat warnings for non-Open-Finance connectors, plan-based filtering (PF vs PJ), the requirement for keywords with a hint fallback, and that it never returns the full catalog. These go beyond what annotations provide and are critical for correct use.

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 a single dense paragraph but every sentence carries unique information. It is front-loaded with the core purpose and return details, followed by caveats and usage instructions. Slightly long but not wasteful; the structure could be improved with breaks, yet each clause earns its place.

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 two-parameter tool with no output schema, the description covers all essential aspects: what it returns (id, access, audience, connections, connect_url), edge cases (caveat, plan restrictions, missing keywords), and how to invoke it. It is self-contained and leaves no major gaps for an agent to determine correct usage.

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 0%, but the description fully explains both parameters: keywords[] with an example ('nubank','btg') and requiredness, and include_accounts with the effect 'returns accounts when true'. It also clarifies the keyword requirement's behavioral consequence (returns a hint if absent), adding meaning the schema lacks.

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 clearly states the tool's function: 'Searches the available bank connectors by name' and lists specific return fields (connector id, access, audience, connections, connect_url). It distinguishes from sibling tools like 'connect' by positioning it as a pre-connect search step, and from 'marketplace' by explicitly noting it never dumps the whole catalog.

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?

Explicitly directs when to use the tool: 'Call this BEFORE connecting to hand the user a one-click link to the right bank.' It also provides contextual guidance on caveats and plan behavior. It does not explicitly name alternative tools for other scenarios, but the 'before connecting' instruction and search-filtered nature give strong usage context.

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