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

The description discloses meaningful behavior beyond annotations: it infers providers from the company's own transactions and filters out any already connected. It also reassures read-only behavior in plain language, which adds strong context though the redundancy with annotations is minor.

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 three sentences are focused, but 'Read-only — it writes nothing' is redundant with the already-provided readOnlyHint annotation. The main behavior is front-loaded and clear, but the redundancy weakens the conciseness relative to the ideal.

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 one-parameter read-only tool with an output schema, the description covers the behavior well, but the total silence about the parameter leaves a real gap. An agent selecting and invoking the function still needs to guess what 'companyId' is and why it is not required. It is not fully complete without that detail.

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?

The schema has a single parameter 'companyId' with no description, and the description never mentions it. With schema description coverage at 0%, the description is responsible for compensating, but it offers no explanation of what to pass or how the CompanyI is used. The agent has to rely on intuition from the parameter name alone.

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: it reports providers the company is already paying for, based on its own transactions, and excludes already connected ones. This clearly distinguishes it from other 'suggest' tools like transaction_suggest_transaction_category or accounting_suggest_statement_matches, and even implicitly contrasts with StartConnection (the follow-up write action).

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 provides clear context: use it when you need a list of providers the company already pays but can't find connected elsewhere, and it even routes to the next step (StartConnection). It does not, however, explicitly mention when not to use it or compare itself to sibling 'suggest' tools, so it lacks exclusions.

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