Score Analysis

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

The readOnlyHint=true annotation already declares this is a safe read operation. The description adds no behavioral context beyond that – nothing about the report object's expected shape, how disagreement is computed, or whether session_id state is mutated. The version requirement is a small useful context clue the annotations don't provide, warranting a baseline 3 rather than 2.

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 single sentence is dense but front-loads the key claim (separate deterministic/model scores). However, it tries to pack three distinct concerns (scores, cost, disagreement) into one confusingly worded clause, and ends with a version note. Not wasteful, but not clean either.

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?

The tool takes a nested report object as a required parameter with no output schema and no documented shape. Given the complexity (nested object, shared state via session_id), the description is far too terse to explain what the tool expects or produces. An agent would need to inspect the schema source to call this correctly.

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 50%. The 'report' parameter has no schema description at all, and the description doesn't explain what shape or fields it must contain. Only 'session_id' is documented in the schema. With a nested-object required param completely undocumented in both description and schema, this is a significant gap.

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 reads 'Report deterministic and model-based scores separately, judge cost... and evaluator disagreement' – it's phrased as an instruction, not a clear statement of what resource the tool operates on. It's unclear whether this scores an analysis, generates a report, or extracts scores from a report object. The name 'score_analysis' combined with this ambiguity makes the purpose hard to pin down, and it doesn't differentiate from siblings like lens.report_summary or lens.audit_report.

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?

No explicit when-to-use or when-not-to guidance. The mention of a version requirement (agenticlens>=0.7.0) is a prerequisite, but there's no indication of when an agent should pick this over lens.report_summary, lens.audit_report, or other lens tools. The distinction is left entirely to inference.

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