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

Annotations declare readOnlyHint=true, and the description does not contradict it, even while noting addresses can compute. It adds significant behavioral detail: addresses can compute aggregates, a non-2xx response is a valid result, and a miss lists fields/params the node holds. This goes beyond the annotation and prepares the agent for nuanced outcomes.

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 long but packed with necessary examples and nuances. It front-loads the core purpose, then systematically explains address formats, compute behavior, and response handling. While every sentence earns its place, its length might be slightly reduced by moving some examples to a separate section, but it's highly effective as is.

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 single-parameter tool with no output schema, the description exhaustively covers input semantics, edge cases (404s), and expected results (typed envelope, miss details). It leaves no ambiguity about how to construct or interpret the tool's behavior, making it fully self-contained.

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 describes 'address' as a same-host path, but the description enriches it with concrete examples, explains accepted formats, and ties them to real use cases (e.g., count, sum, filter). It also clarifies that addresses can be obtained from search or other drill results, giving the agent full context for parameter construction.

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 fetches a drillable.com address and returns its typed envelope (record, grades, abstains, related actions). It explicitly distinguishes from search by noting that enumeration/count questions are better served by drilling the right address, not searching, and provides specific address formats for different use cases.

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 offers explicit guidance on when to use this tool: pass an address from search or a link in another drill result. It explains compute/aggregate use cases and clarifies that non-2xx responses are valid, informative results rather than errors, which is crucial for correct handling. It also implies when not to use (search for discovery) and gives alternative contexts.

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