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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states that the tool is metered and debits from the caller's wallet, with a specific surcharge formula, which is valuable. However, it does not explicitly confirm that the operation is read-only, does not describe the output format or size, and does not mention any side effects beyond cost. The cost transparency is strong, but other behavioral aspects remain under-specified.

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 sentence with a dash, front-loading the purpose before diving into billing details. It is not overly long, but a significant portion (roughly half) is devoted to pricing mechanics, which, while useful, could be condensed. The structure is logical and efficient, but the focus on billing might distract from the core functionality.

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?

Given the tool's simplicity (one parameter, no output schema, no annotations), the description should at least outline the return structure or mention any limits on the graph neighbourhood. It does neither. The description explains cost thoroughly but leaves the agent guessing about what data will be returned and whether there are any restrictions (e.g., depth of neighbourhood, pagination). This is a significant gap for an agent deciding whether to call the tool.

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 input schema has a single required 'id' string, and the description mentions 'by id' but does not elaborate on what the id represents (e.g., a company identifier, UUID format, or any constraints). With schema coverage at 0%, the description fails to compensate by clarifying the parameter's purpose or format beyond the schema itself. The phrase 'by id' is minimal and does not add meaningful semantic value.

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 'One company's record and graph neighbourhood by id', which conveys the core action of retrieving a company's data and its connections. It is specific about the resource (company) and the scope (record and graph neighbourhood), and it distinguishes itself from siblings like 'relationships' or 'nearby' by focusing on a single company's full neighbourhood rather than a general graph operation. However, it lacks an explicit verb like 'fetch' or 'get', making it slightly less direct than ideal.

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 extensive billing guidance, pointing to tools like 'billing_quote' and 'joules_deficit' for cost checks, but it never explains when to use this tool versus its many siblings. There is no mention of scenarios where 'relationships' or 'hops' would be preferable, nor any exclusion criteria. The pricing context is useful but does not substitute for usage direction.

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