uma_score

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

With no annotations, the description carries the full burden. It discloses core behavior: it segments the context into sentences, scores each against the query using a 'local cross-encoder,' and applies no threshold. This gives a clear safety profile (read-only, no side effects). Minor gaps include the exact sentence segmentation rules and the output format, but overall it is transparent for the tool's simplicity.

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 and well-structured. It opens with a clear one-sentence summary, then adds operational detail (sentence segmentation, local encoder, no threshold), and ends with a practical use case. Every sentence earns its place, with no verbosity or repetition.

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 (two string parameters, no nested objects) and lack of output schema, the description is nearly complete. It explains what the tool does, how it works, and a typical use case. The only notable omission is the precise return format (e.g., a list of scores vs. sentence-score pairs), which an agent might need to fully interpret results.

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 0%, so the description must clarify parameter meaning. It does add some semantics: 'context' is segmented into sentences, and 'query' is the reference for relevance scoring. However, it does not elaborate on types, constraints, or usage examples beyond the names, leaving some ambiguity about how the parameters interact with the output.

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 returns per-sentence cross-encoder relevance scores for a context, which is specific and actionable. It distinguishes itself from siblings by explicitly noting 'without applying any threshold' and framing the purpose as 'inspecting why Uma would keep or drop a given sentence,' which contrasts with filtering (uma_filter) and aggregation (uma_stats) tools.

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 a clear use case: 'Useful for inspecting why Uma would keep or drop a given sentence.' This implies when to use the tool (for understanding per-sentence scoring before thresholding) and hints at not using it for thresholded filtering. However, it does not explicitly mention alternative tools or state when not to use it, so it falls slightly short of full guidance.

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