Get Tolerance Landscape

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive. The description adds value by disclosing cache-first behavior, the possibility of returning a 'processing' status instead of an error, and the need to poll after poll_after_s. It also explains the inclusive nature of position range slicing.

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 concise (about 4 sentences) and well-structured: what the tool returns, optional parameters, behavior when processing, and a signature example. Every sentence adds value without redundancy.

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 tool with 6 parameters and no output schema, the description covers the main aspects: return data (Pfam domains and per-residue annotations), parameter usage (slicing, pagination), and important behavior (cache-first, processing status). It could elaborate on the exact output structure, but the conceptual description is sufficient for most use cases.

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 coverage is 100% with clear parameter descriptions. The description adds context by emphasizing the inclusive residue range for position_start/position_stop and stating that limit/offset are for pagination. While not essential, it reinforces parameter relationships.

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 explicitly states it returns the MetaDome tolerance landscape for a built transcript, including Pfam domains and per-residue annotations. It also mentions cache-first behavior and the optional slicing by residue range, making the purpose very specific and distinguishable from siblings like request_tolerance_landscape.

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 clearly indicates when to use this tool: to get the tolerance landscape if available, and if the build is still running, it returns a processing status to poll again. It implicitly suggests using request_tolerance_landscape if the build has not started, but does not explicitly state this alternative, which would improve the score.

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