get_spec

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

No annotations are provided, so the description takes full responsibility. It discloses that calling this tool alongside assess_result duplicates payload, that the spec descriptions are this implementation's own wording and not the redistributable published text, and that published question IDs ensure interoperability. These are meaningful behavioral traits beyond a simple 'return spec'. It doesn't explicitly mention permissions or side effects, but 'Return' suggests a read-only operation.

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 organized into three focused paragraphs: what it returns, usage guidance, and a legal/behavioral caveat. The first sentence front-loads the core purpose, and every subsequent sentence adds distinct value—no filler. Despite being longer than some tool descriptions, this length is justified by the need to cover copyright and duplication warnings.

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 complexity and the presence of an output schema (which handles return-value details), the description covers the essential context: purpose, usage, parameter semantics for detail, and licensing limitations. The only gap is the unexplained spec_version parameter, though its name and default make it reasonably clear. Overall, the description provides a complete picture for an optional introspection 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 description thoroughly explains the detail parameter: 'detail="compact" (default) gives question ids, own-words labels, response options and evidence modes; detail="full" adds every intent and assessor note.' However, it does not explain the spec_version parameter, which is only inferable from its name and default value. With schema description coverage at 0%, this partial compensation is adequate but not complete.

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 opens with 'Return the encoded ROBINS-I V2 specification' and enumerates its contents (preliminaries, signalling questions, response vocabularies, etc.), which is a specific verb+resource. It also distinguishes itself from assess_result by explicitly labeling itself as 'OPTIONAL in the assessment flow — introspection only', making the tool's role clear.

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 gives explicit usage guidance: 'OPTIONAL in the assessment flow — introspection only. assess_result already carries the rubric for the domain in hand, so calling both duplicates the payload.' This tells the agent when to use it, when not to, and names the alternative. It also explains the difference between compact and full detail, guiding parameter selection.

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