Get Company Exchange Rates

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

The description adds useful failure-mode info (401, 403, 404) and empty-array behavior, but it also contradicts itself about returning a collection vs a single object. Annotations already cover read-only/idempotence, so the main behavioral additions are undermined by the internal inconsistency about response shape.

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 overly long and repetitive, with three conflicting 'Returns' statements. Key facts like endpoint and error codes are useful, but the contradictory wording could have been avoided with a single clear statement about list vs single object. It lacks coherent structure.

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 simple GET tool, the description should clearly state whether the response is a list or an object; it fails to do so. The error-code details are valuable, but the array/object confusion is a critical gap, especially with no output schema to clarify. Overall, the description does not provide enough reliable context to invoke the tool 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?

Company_id is already fully documented in the schema (100% coverage), so the baseline is 3. However, the description adds a contradictory claim that company_id defaults when omitted, while also stating 'Required parameters: company_id' and the schema marks it required. This ambiguous extra information detracts from schema clarity.

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 initially says 'Returns the collection of active company-level exchange rates,' but later says 'Returns a single JSON object' and 'Use this when you already know which company exchange rate you want,' creating ambiguity about whether this is a list or show operation. It distinguishes company-level from project-level siblings, but the internal contradiction makes the core purpose unclear.

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 provides some context ('Use this when you already know which company exchange rate you want'), but this is misleading for a collection endpoint and does not explain when to use an alternative like get_project_exchange_rates or a show-style tool. No explicit when-not or alternative guidance is given.

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